ruihan/qwen38-flash-next-rtx6000d
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare MTP steps and prefill batches; retain qualified MTP 2 baseline

Browse Source
This commit is contained in:
ruihan
2026-09-18 23:22:45 +08:00
parent 918b78a3b8
commit c8bfe6b9ab
45 changed files with 3785 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
audit/tuning/steps-123/mtp2-b2048/compose.yaml
+46
View File
@@ -0,0 +1,46 @@
name: qwen38-flash-rtx6000d
services:
vllm:
image: local/qwen38-flash-6000d:0bfc7a15
build: .
container_name: qwen38-flash-6000d
gpus: all
shm_size: 8g
mem_limit: 210g
memswap_limit: 210g
restart: "no"
ports:
- "${BIND_ADDRESS:-127.0.0.1}:${API_PORT:-8000}:8000"
environment:
HF_HUB_OFFLINE: "1"
VLLM_USE_V2_MODEL_RUNNER: "1"
VLLM_WORKER_MULTIPROC_METHOD: spawn
OMP_NUM_THREADS: "8"
TORCHINDUCTOR_COMPILE_THREADS: "2"
CUTE_DSL_ARCH: sm_120a
volumes:
- /data/flash-next/models/nvidia-Qwen3.8-Flash-Next-NVFP4:/model:ro
- /data/flash-next/cache:/root/.cache
- ./secrets/api-key:/run/secrets/api-key:ro
entrypoint: ["/bin/bash", "-lc"]
command:
- >-
exec vllm serve /model
--served-model-name qwen3.8-flash-next
--host 0.0.0.0 --port 8000
--tensor-parallel-size 1 --dtype bfloat16
--engram-config '{"cpu_offload":true}'
--kv-cache-dtype fp8 --gpu-memory-utilization 0.985
--max-model-len 131072 --max-num-seqs 1 --max-num-batched-tokens 2048
--enable-chunked-prefill --enable-prefix-caching
--speculative-config '{"method":"mtp","num_speculative_tokens":2}'
--compilation-config '{"mode":0,"cudagraph_mode":"FULL","cudagraph_capture_sizes":[1,3]}' --no-enable-flashinfer-autotune
--load-format safetensors
--reasoning-parser qwen3 --tool-call-parser qwen3_xml --enable-auto-tool-choice
--api-key "$$(cat /run/secrets/api-key)"
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5)"]
interval: 30s
timeout: 10s
retries: 5
start_period: 30m
audit/tuning/steps-123/mtp2-b2048/mtp-metrics.txt
+26
View File
@@ -0,0 +1,26 @@
# HELP vllm:spec_decode_num_drafts_total Number of spec decoding drafts.
# TYPE vllm:spec_decode_num_drafts_total counter
vllm:spec_decode_num_drafts_total{engine="0",model_name="qwen3.8-flash-next"} 52554.0
# HELP vllm:spec_decode_num_drafts_created Number of spec decoding drafts.
# TYPE vllm:spec_decode_num_drafts_created gauge
vllm:spec_decode_num_drafts_created{engine="0",model_name="qwen3.8-flash-next"} 1.7897410011528008e+09
# HELP vllm:spec_decode_num_draft_tokens_total Number of draft tokens.
# TYPE vllm:spec_decode_num_draft_tokens_total counter
vllm:spec_decode_num_draft_tokens_total{engine="0",model_name="qwen3.8-flash-next"} 105108.0
# HELP vllm:spec_decode_num_draft_tokens_created Number of draft tokens.
# TYPE vllm:spec_decode_num_draft_tokens_created gauge
vllm:spec_decode_num_draft_tokens_created{engine="0",model_name="qwen3.8-flash-next"} 1.7897410011528184e+09
# HELP vllm:spec_decode_num_accepted_tokens_total Number of accepted tokens.
# TYPE vllm:spec_decode_num_accepted_tokens_total counter
vllm:spec_decode_num_accepted_tokens_total{engine="0",model_name="qwen3.8-flash-next"} 69785.0
# HELP vllm:spec_decode_num_accepted_tokens_created Number of accepted tokens.
# TYPE vllm:spec_decode_num_accepted_tokens_created gauge
vllm:spec_decode_num_accepted_tokens_created{engine="0",model_name="qwen3.8-flash-next"} 1.7897410011528296e+09
# HELP vllm:spec_decode_num_accepted_tokens_per_pos_total Accepted tokens per draft position.
# TYPE vllm:spec_decode_num_accepted_tokens_per_pos_total counter
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3.8-flash-next",position="0"} 40257.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3.8-flash-next",position="1"} 29528.0
# HELP vllm:spec_decode_num_accepted_tokens_per_pos_created Accepted tokens per draft position.
# TYPE vllm:spec_decode_num_accepted_tokens_per_pos_created gauge
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3.8-flash-next",position="0"} 1.7897410011528459e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3.8-flash-next",position="1"} 1.78974100115285e+09
audit/tuning/steps-123/mtp2-b2048/quality-medium.jsonl
+7
View File
@@ -0,0 +1,7 @@
{"name": "invoice-extraction", "passed": true, "elapsed_s": 1.2711202999998932, "response": {"id": "chatcmpl-acf4252c63733754", "object": "chat.completion", "created": 1789743196, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": "\n\n{\"supplier\":\"North Star Ltd\",\"currency\":\"CNY\",\"total\":476,\"due_date\":\"2026-10-03\"}", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": "The user wants me to extract invoice data into JSON format. Let me parse the information:\n\n- Supplier: North Star Ltd\n- Currency: CNY\n- Rows: 3 items at 125 each = 375, 2 items at 48 each = 96\n- Shipping: 20\n- Discount: 15\n- Total: 375 + 96 + 20 - 15 = 476\n- Due date: 2026-10-03\n\nThe total must be an integer: 476\n\nKeys required: supplier, currency, total, due_date\n\nLet me format as JSON only.\n"}, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 90, "total_tokens": 275, "completion_tokens": 185, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 150}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
{"name": "deduplicate", "passed": true, "elapsed_s": 1.7527402949999669, "response": {"id": "chatcmpl-82388a5e0c331239", "object": "chat.completion", "created": 1789743198, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": "\n\n{\"ids\":[\"A\",\"B\",\"D\"],\"total\":48}", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": "Let me process the orders step by step.\n\nInput orders:\n1. A pending 12\n2. B paid 20\n3. A paid 15\n4. C cancelled 99\n5. D paid 8\n6. B paid 25\n\nStep 1: Keep the last occurrence of each ID.\n- A: last occurrence is \"A paid 15\" (order 3)\n- B: last occurrence is \"B paid 25\" (order 6)\n- C: last occurrence is \"C cancelled 99\" (order 4)\n- D: last occurrence is \"D paid 8\" (order 5)\n\nStep 2: Discard cancelled orders.\n- C is cancelled, so discard it.\n- Remaining: A paid 15, B paid 25, D paid 8\n\nStep 3: Sort IDs alphabetically.\n- A, B, D\n\nStep 4: Calculate total.\n- 15 + 25 + 8 = 48\n\nOutput: {\"ids\":[\"A\",\"B\",\"D\"],\"total\":48}\n"}, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 78, "total_tokens": 342, "completion_tokens": 264, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 247}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
{"name": "schedule", "passed": true, "elapsed_s": 2.0548892629958573, "response": {"id": "chatcmpl-b59f8d39ded5a629", "object": "chat.completion", "created": 1789743199, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": "\n\n{\"earliest_finish\":10,\"critical_path\":[\"A\",\"B\",\"D\"]}", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": "Let me analyze this scheduling problem carefully.\n\nJobs and their durations:\n- A: 3 hours (starts at hour 0)\n- B: 5 hours, starts after A\n- C: 4 hours, starts after A\n- D: 2 hours, starts after both B and C\n\nLet me trace the timeline:\n\n- A starts at hour 0, finishes at hour 3.\n- B starts after A → starts at hour 3, finishes at hour 3+5 = 8.\n- C starts after A → starts at hour 3, finishes at hour 3+4 = 7.\n- D starts after both B and C → starts at max(8, 7) = 8, finishes at 8+2 = 10.\n\nEarliest finish: 10 hours.\n\nCritical path: The longest path through the dependency graph.\n- Path A → B → D: 3 + 5 + 2 = 10\n- Path A → C → D: 3 + 4 + 2 = 9\n\nThe critical path is A → B → D with total duration 10.\n\nSo critical_path = [\"A\", \"B\", \"D\"]\nearliest_finish = 10\n"}, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 68, "total_tokens": 359, "completion_tokens": 291, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 271}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
{"name": "chinese-policy", "passed": true, "elapsed_s": 1.3326087149980594, "response": {"id": "chatcmpl-8e1cd6b923cb571c", "object": "chat.completion", "created": 1789743201, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": "\n\n{\"甲\":\"主管\",\"乙\":\"经理\",\"丙\":\"经理\",\"丁\":\"总监\"}", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": "让我仔细分析审批制度：\n\n- 金额不超过5000元：主管审批\n- 超过5000且不超过20000：经理审批\n- 超过20000：总监审批\n- 加急不改变审批人\n\n现在分析各申请：\n\n甲：5000元 → 不超过5000 → 主管\n乙：5001元加急 → 超过5000且不超过20000 → 经理（加急不改变审批人）\n丙：20000元 → 超过5000且不超过20000 → 经理\n丁：20001元 → 超过20000 → 总监\n\n输出JSON格式。\n"}, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 106, "total_tokens": 295, "completion_tokens": 189, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 169}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
{"name": "merge-intervals", "passed": true, "validation_stdout": "passed\n", "validation_stderr": "", "response": {"id": "chatcmpl-848dfe0da82871ae", "object": "chat.completion", "created": 1789743203, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": "\n\n{\"code\": \"def merge_intervals(intervals):\\n if len(intervals) == 0:\\n return []\\n sorted_intervals = sorted(intervals)\\n merged = [sorted_intervals[0].copy()]\\n for i in range(1, len(sorted_intervals)):\\n current = sorted_intervals[i]\\n last = merged[len(merged) - 1]\\n if current[0] <= last[1]:\\n last[1] = max(last[1], current[1])\\n else:\\n merged.append(current.copy())\\n return merged\"}", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": "The user wants a Python function `merge_intervals` that merges overlapping integer intervals, including touching endpoints. Let me think about the requirements:\n\n1. Merge overlapping intervals, including touching endpoints (e.g., [1,3] and [3,5] should merge to [1,5])\n2. Return sorted merged intervals as lists\n3. Reply ONLY a JSON object with a code string\n4. No imports, type annotations, decorators, top-level statements or helper functions\n5. Allowed builtins: sorted, len, range, min, max, list, enumerate, sum\n6. Allowed methods: append, sort, copy\n\nLet me write the function:\n\n```python\ndef merge_intervals(intervals):\n if len(intervals) == 0:\n return []\n sorted_intervals = sorted(intervals, key=lambda x: x[0])\n merged = [sorted_intervals[0].copy()]\n for i in range(1, len(sorted_intervals)):\n current = sorted_intervals[i]\n last = merged[len(merged) - 1]\n if current[0] <= last[1]:\n last[1] = max(last[1], current[1])\n else:\n merged.append(current.copy())\n return merged\n```\n\nWait, I need to check - can I use lambda? The allowed builtins are: sorted, len, range, min, max, list, enumerate, sum. Lambda isn't explicitly listed but it's a language construct, not a builtin. Let me think... `sorted` with a key function requires a callable. I could use `sorted(intervals)` since lists sort lexicographically by default, which would sort by first element then second element. That works for intervals!\n\nActually, `sorted(intervals)` on a list of lists will sort by the first element, then second element. That's exactly what we need.\n\nLet me also check: can I use `lambda`? It's not a builtin, it's a keyword/expression. The restriction says \"no imports, type annotations, decorators, top-level statements or helper functions.\" Lambda isn't a helper function per se, it's an anonymous function expression. But to be safe, let me just use `sorted(intervals)` without a key since default sorting of lists works correctly for intervals.\n\nAlso, I need to be careful about `.copy()` - it's in the allowed methods list. And `.append()` and `.sort()` are allowed.\n\nLet me also check: `len(merged) - 1` to get the last index - that's fine.\n\nLet me also make sure I'm not using any disallowed things. No type annotations, no decorators, no top-level statements, no helper functions. The function itself is fine.\n\nLet me format as JSON with a \"code\" key.\n\n```json\n{\"code\": \"def merge_intervals(intervals):\\n if len(intervals) == 0:\\n return []\\n sorted_intervals = sorted(intervals)\\n merged = [sorted_intervals[0].copy()]\\n for i in range(1, len(sorted_intervals)):\\n current = sorted_intervals[i]\\n last = merged[len(merged) - 1]\\n if current[0] <= last[1]:\\n last[1] = max(last[1], current[1])\\n else:\\n merged.append(current.copy())\\n return merged\"}\n```\n\nWait, I should double-check: `sorted(intervals)` on a list of lists like `[[1,3],[2,6],[8,10]]` will sort correctly by first element. Yes, Python's default list comparison is lexicographic, so it compares element by element. This is correct for our use case.\n\nAlso checking: touching endpoints means [1,3] and [3,5] merge. My condition `current[0] <= last[1]` handles this since 3 <= 3 is true.\n\nThis looks good. Let me format the JSON properly.\n"}, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 81, "total_tokens": 1071, "completion_tokens": 990, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 857}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
{"name": "binary-search", "passed": true, "validation_stdout": "passed\n", "validation_stderr": "", "response": {"id": "chatcmpl-acbd27655cbcc931", "object": "chat.completion", "created": 1789743210, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": "\n\n{\"code\": \"def lower_bound(nums, target):\\n lo = 0\\n hi = len(nums)\\n while lo < hi:\\n mid = (lo + hi) // 2\\n if nums[mid] < target:\\n lo = mid + 1\\n else:\\n hi = mid\\n return lo\"}", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": "The user wants a Python function `lower_bound` that finds the index of the first element >= target in a sorted list `nums`, or `len(nums)` if none exists.\n\nConstraints:\n- Return ONLY a JSON object with a \"code\" string\n- No imports, type annotations, decorators, top-level statements, or helper functions\n- Allowed builtins: sorted, len, range, min, max, list, enumerate, sum\n- Allowed methods: append, sort, copy\n\nLet me write a binary search implementation for lower_bound:\n\n```python\ndef lower_bound(nums, target):\n lo = 0\n hi = len(nums)\n while lo < hi:\n mid = (lo + hi) // 2\n if nums[mid] < target:\n lo = mid + 1\n else:\n hi = mid\n return lo\n```\n\nThis is a standard binary search for lower bound. Let me check constraints:\n- No imports ✓\n- No type annotations ✓\n- No decorators ✓\n- No top-level statements ✓\n- No helper functions ✓\n- Uses `len` which is allowed ✓\n- Uses basic operators and comparisons ✓\n\nNow I need to wrap this in a JSON object with a \"code\" string.\n"}, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 92, "total_tokens": 438, "completion_tokens": 346, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 269}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
{"name": "tool-arguments", "passed": true, "response": {"id": "chatcmpl-aa08e51120ea5d43", "object": "chat.completion", "created": 1789743212, "model": "qwen3.8-flash-next", "choices": [{"index": 0, "message": {"role": "assistant", "content": null, "refusal": null, "annotations": null, "audio": null, "function_call": null, "tool_calls": [{"id": "chatcmpl-tool-80911c02057f9d71", "type": "function", "function": {"name": "create_ticket", "arguments": "{\"title\": \"GPU cooling failure\", \"priority\": \"urgent\", \"asset\": \"GPU-092\"}"}}], "reasoning": "The user wants me to create a ticket with specific parameters:\n- title: \"GPU cooling failure\" (exactly)\n- priority: \"urgent\"\n- asset: \"GPU-092\" (exactly)\n\nThis is straightforward - I'll call the create_ticket function with these exact values.\n"}, "logprobs": null, "finish_reason": "tool_calls", "stop_reason": null, "token_ids": null, "routed_experts": null}], "service_tier": null, "system_fingerprint": "vllm-0.3.1.dev3+g0bfc7a15d-9e1c6e32", "usage": {"prompt_tokens": 325, "total_tokens": 447, "completion_tokens": 122, "prompt_tokens_details": null, "completion_tokens_details": {"reasoning_tokens": 65}}, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null, "ec_transfer_params": null, "metrics": null}}
audit/tuning/steps-123/mtp2-b2048/quality-medium.jsonl.log
+8
View File
@@ -0,0 +1,8 @@
{"name": "invoice-extraction", "passed": true, "elapsed_s": 1.2711202999998932}
{"name": "deduplicate", "passed": true, "elapsed_s": 1.7527402949999669}
{"name": "schedule", "passed": true, "elapsed_s": 2.0548892629958573}
{"name": "chinese-policy", "passed": true, "elapsed_s": 1.3326087149980594}
{"name": "merge-intervals", "passed": true, "validation_stdout": "passed\n", "validation_stderr": ""}
{"name": "binary-search", "passed": true, "validation_stdout": "passed\n", "validation_stderr": ""}
{"name": "tool-arguments", "passed": true}
QUALITY_COMPLETE
audit/tuning/steps-123/mtp2-b2048/screen.jsonl
+37
View File
File diff suppressed because one or more lines are too long
audit/tuning/steps-123/mtp2-b2048/screen.jsonl.log
+38
View File
@@ -0,0 +1,38 @@
{"name": "arithmetic-0", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 141, "completion_tokens": 82, "completion_tokens_details": {"reasoning_tokens": 75}}, "ttft_s": 0.08033495700510684, "elapsed_s": 0.5909661660043639, "decode_tps": 158.62720212253586, "max_stream_gap_s": 0.018763815001875628, "events": 29, "sha256": "d929fd317464b07ece811a135b5937af8eb36ea0b1e88ec82bc5137102d0a62c"}
{"name": "arithmetic-1", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 96, "completion_tokens": 37, "completion_tokens_details": {"reasoning_tokens": 30}}, "ttft_s": 0.08595889700518455, "elapsed_s": 0.3043062380020274, "decode_tps": 164.87491826392582, "max_stream_gap_s": 0.01860671999747865, "events": 13, "sha256": "5cd050422245af84010bf1c71082001dcd6d880bdd6dd7002e69a8402ab6c73c"}
{"name": "arithmetic-2", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 125, "completion_tokens": 66, "completion_tokens_details": {"reasoning_tokens": 59}}, "ttft_s": 0.08532555599958869, "elapsed_s": 0.5077504829969257, "decode_tps": 153.87349525519303, "max_stream_gap_s": 0.01870621599664446, "events": 24, "sha256": "c6dabe0673abae92ebdac3d245deb7c9ca89c874d316c46b8ce09fde923a752f"}
{"name": "arithmetic-3", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 98, "completion_tokens": 39, "completion_tokens_details": {"reasoning_tokens": 31}}, "ttft_s": 0.08707080200110795, "elapsed_s": 0.32353630300349323, "decode_tps": 160.69997457944905, "max_stream_gap_s": 0.01859223899373319, "events": 14, "sha256": "4f382303f23d66fb4abcb57f3ad914e7f87831db4a3757ab5fdab83d25b58b1b"}
{"name": "arithmetic-4", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 131, "completion_tokens": 72, "completion_tokens_details": {"reasoning_tokens": 64}}, "ttft_s": 0.08545495500584366, "elapsed_s": 0.5441159190013423, "decode_tps": 154.798436259984, "max_stream_gap_s": 0.018821514000592288, "events": 26, "sha256": "5c8a761b69d32970d9e4021e9cddda2caf44a6201a9bf34e503844cd2ce1dc0c"}
{"name": "arithmetic-5", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 101, "completion_tokens": 42, "completion_tokens_details": {"reasoning_tokens": 34}}, "ttft_s": 0.08643778399709845, "elapsed_s": 0.34146275900275214, "decode_tps": 160.7685678592501, "max_stream_gap_s": 0.018947848002426326, "events": 15, "sha256": "38ecdb08b2fcabd6a6a91e18d08f90ca325aae7f5c9ee565aa360e4d3cb610e9"}
{"name": "arithmetic-6", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 130, "completion_tokens": 71, "completion_tokens_details": {"reasoning_tokens": 63}}, "ttft_s": 0.08607953199680196, "elapsed_s": 0.5258115449978504, "decode_tps": 159.18786426821532, "max_stream_gap_s": 0.018670357996597886, "events": 25, "sha256": "7ac565b6322b904ff447bc9ef3ed069ebc4e48b8a51e72f9e18919bd8e3000d1"}
{"name": "arithmetic-7", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 153, "completion_tokens": 94, "completion_tokens_details": {"reasoning_tokens": 86}}, "ttft_s": 0.08593622500484344, "elapsed_s": 0.6902767670035246, "decode_tps": 153.8867468537349, "max_stream_gap_s": 0.018791513997712173, "events": 33, "sha256": "e7b73eb708d2c4c7d2fc5dca2aed40a571c8b0445cd1867d916b47f57ec4cac0"}
{"name": "arithmetic-8", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 144, "completion_tokens": 85, "completion_tokens_details": {"reasoning_tokens": 77}}, "ttft_s": 0.08543285400082823, "elapsed_s": 0.6162005010046414, "decode_tps": 158.2613418021625, "max_stream_gap_s": 0.018708337993302848, "events": 29, "sha256": "9d93671c15eac2005a27c4fe38e5d4285b3feca77fa1e90f138c71a2b5164db8"}
{"name": "arithmetic-9", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 59, "total_tokens": 143, "completion_tokens": 84, "completion_tokens_details": {"reasoning_tokens": 76}}, "ttft_s": 0.08579609300068114, "elapsed_s": 0.6164905580008053, "decode_tps": 156.39884241110482, "max_stream_gap_s": 0.018804239996825345, "events": 29, "sha256": "6b95a8b82a4ba5a8335b5f10899663aeebe71fed7e5673836b82ec74cfa1cbee"}
{"name": "arithmetic-10", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 60, "total_tokens": 143, "completion_tokens": 83, "completion_tokens_details": {"reasoning_tokens": 75}}, "ttft_s": 0.08569144899956882, "elapsed_s": 0.5975101969961543, "decode_tps": 160.21296664292387, "max_stream_gap_s": 0.018605278004542924, "events": 29, "sha256": "662f32768d742ea67e45b8109190fc2ba55c429346f4be9b9492ff457cdacc48"}
{"name": "arithmetic-11", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 61, "total_tokens": 151, "completion_tokens": 90, "completion_tokens_details": {"reasoning_tokens": 82}}, "ttft_s": 0.08546528800070519, "elapsed_s": 0.6353967890026979, "decode_tps": 161.8383377526822, "max_stream_gap_s": 0.018794105999404564, "events": 31, "sha256": "cdbf70494a3484ed891137af4bad12b7417009befd921930fc1fa5e5e3907e27"}
{"name": "json", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 66, "total_tokens": 109, "completion_tokens": 43, "completion_tokens_details": {"reasoning_tokens": 26}}, "ttft_s": 0.08568278700113297, "elapsed_s": 0.37689909800246824, "decode_tps": 144.2226908773919, "max_stream_gap_s": 0.018781819999276195, "events": 17, "sha256": "2acba5868b21fa90ff7d281b66898b4ed66b6ff2f42a3d5a1d5bd11569806949"}
{"name": "multiturn", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 82, "total_tokens": 145, "completion_tokens": 63, "completion_tokens_details": {"reasoning_tokens": 51}}, "ttft_s": 0.08570619000238366, "elapsed_s": 0.5379072569994605, "decode_tps": 137.10715105499912, "max_stream_gap_s": 0.018587483995361254, "events": 26, "sha256": "dd12a39a5152c7bd1ce0e00fedc430e10a83c25c8a7850e9be06dcc0b4fe0353"}
{"name": "image-ocr", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 3135, "total_tokens": 3276, "completion_tokens": 141, "completion_tokens_details": {"reasoning_tokens": 102}}, "ttft_s": 0.37922176600113744, "elapsed_s": 1.3786603870030376, "decode_tps": 140.07863720500933, "max_stream_gap_s": 0.01991734900366282, "events": 54, "sha256": "9e3c14a4e0973d378dc3fda85c529bfed85154aefd90d72c8313c78df80f6564"}
{"name": "video-120s", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 12069, "total_tokens": 12213, "completion_tokens": 144, "completion_tokens_details": {"reasoning_tokens": 130}}, "ttft_s": 0.8094746360002318, "elapsed_s": 1.7980530589993577, "decode_tps": 144.65215573507055, "max_stream_gap_s": 0.018804600993462373, "events": 55, "sha256": "40374d1d01e9d30a2e10dfcf6ba861c98b6c27c52bed2fc369e82286625e2f93"}
{"name": "multi-image", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 12356, "total_tokens": 12433, "completion_tokens": 77, "completion_tokens_details": {"reasoning_tokens": 66}}, "ttft_s": 1.4533180090002134, "elapsed_s": 1.9994508850068087, "decode_tps": 139.16027278145802, "max_stream_gap_s": 0.018682743997487705, "events": 31, "sha256": "6948cfaa73343b43893c8bbd5a7faf45ed78d55ac8ae50d67b8b890a8d1bf6c7"}
{"name": "warmup-code", "passed": true, "finish": "length", "usage": {"prompt_tokens": 77, "total_tokens": 333, "completion_tokens": 256, "completion_tokens_details": {"reasoning_tokens": 256}}, "ttft_s": 0.08620800900098402, "elapsed_s": 2.189102151998668, "decode_tps": 121.26145333996531, "max_stream_gap_s": 0.018632254999829456, "events": 117, "sha256": "ae01d596ec7a45f3c398b1526e5f345c2a100644fe1e8d2975c98d406465b7ad"}
{"name": "perf-code-0", "passed": true, "finish": "length", "usage": {"prompt_tokens": 77, "total_tokens": 2125, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 2048}}, "ttft_s": 0.07210104499972658, "elapsed_s": 16.617303178005386, "decode_tps": 123.72166768011161, "max_stream_gap_s": 0.019507625998812728, "events": 920, "sha256": "4b5a99c6a2d74362c14314126d243ab0ea75f0d203a637e5635b96bc429e3afb"}
{"name": "perf-code-1", "passed": true, "finish": "length", "usage": {"prompt_tokens": 77, "total_tokens": 2125, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 2048}}, "ttft_s": 0.07450222100305837, "elapsed_s": 16.60604691500339, "decode_tps": 123.82387961258709, "max_stream_gap_s": 0.018462731000909116, "events": 922, "sha256": "c6a65a378e367e11250c85739caf6c8d1093bd987b88899767d97d623c15bcb9"}
{"name": "perf-code-2", "passed": true, "finish": "length", "usage": {"prompt_tokens": 77, "total_tokens": 2125, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 2048}}, "ttft_s": 0.08693470500293188, "elapsed_s": 16.638716553999984, "decode_tps": 123.67248545654539, "max_stream_gap_s": 0.018704524001805112, "events": 923, "sha256": "c6aab7182e88cf796f5b16f8b786142eb9521c9123cb0a049524dde6362b299f"}
{"name": "warmup-chinese", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 335, "completion_tokens": 256, "completion_tokens_details": {"reasoning_tokens": 182}}, "ttft_s": 0.07400395700096851, "elapsed_s": 1.9887343450027402, "decode_tps": 133.17801900356326, "max_stream_gap_s": 0.0185166260052938, "events": 108, "sha256": "c7ecb8327c0218df2d04be1c67cec8ee285dd526519e8615316908f083855b7c"}
{"name": "perf-chinese-0", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 2127, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 182}}, "ttft_s": 0.08585922900238074, "elapsed_s": 15.984570784006792, "decode_tps": 128.75257173627188, "max_stream_gap_s": 0.01882019199547358, "events": 889, "sha256": "d4c974412272e4560fbce42c1ad1cf265991e6545fd8518f4c0823f8c56bc7ea"}
{"name": "perf-chinese-1", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 2127, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 182}}, "ttft_s": 0.07313994099968113, "elapsed_s": 15.988134749000892, "decode_tps": 128.62083994968555, "max_stream_gap_s": 0.018578499999421183, "events": 890, "sha256": "8fc19ac2a6425782e63b5c26dd326f7124bce54fc957913963c9fc6ae4ee3341"}
{"name": "perf-chinese-2", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 2127, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 182}}, "ttft_s": 0.08644359100435395, "elapsed_s": 15.966877792001469, "decode_tps": 128.90075762988087, "max_stream_gap_s": 0.018619577000208665, "events": 888, "sha256": "488769996df35d3bbedd2a91046c0a137677097523f73433b0919b61c68071b5"}
{"name": "warmup-reasoning", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 335, "completion_tokens": 256, "completion_tokens_details": {"reasoning_tokens": 256}}, "ttft_s": 0.07434646700130543, "elapsed_s": 2.126096015002986, "decode_tps": 124.28417505848094, "max_stream_gap_s": 0.01840589300263673, "events": 116, "sha256": "d557c88f4473c4da0f26d8a2bfdb8aae0734ac1d790d7d3f74c26151b5cbe509"}
{"name": "perf-reasoning-0", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 2127, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 2048}}, "ttft_s": 0.07352274699951522, "elapsed_s": 16.837296222998702, "decode_tps": 122.10854572395078, "max_stream_gap_s": 0.018720656000368763, "events": 935, "sha256": "eec62c20975cfeaada4ad14ef0f726db52eaff6b498dcbbf3f5f515c2c5725c8"}
{"name": "perf-reasoning-1", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 2127, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 2048}}, "ttft_s": 0.07170502199733164, "elapsed_s": 16.85341221699491, "decode_tps": 121.97805480780796, "max_stream_gap_s": 0.01876352399995085, "events": 936, "sha256": "8a7cb2cde52eee53562fd48aca68d5267dceb315e35b12b86822b67066eacf58"}
{"name": "perf-reasoning-2", "passed": true, "finish": "length", "usage": {"prompt_tokens": 79, "total_tokens": 2127, "completion_tokens": 2048, "completion_tokens_details": {"reasoning_tokens": 2048}}, "ttft_s": 0.07260531799693126, "elapsed_s": 16.818446777993813, "decode_tps": 122.23930370354654, "max_stream_gap_s": 0.01878616500471253, "events": 934, "sha256": "eec62c20975cfeaada4ad14ef0f726db52eaff6b498dcbbf3f5f515c2c5725c8"}
{"name": "long-context-0", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 125995, "total_tokens": 126111, "completion_tokens": 116, "completion_tokens_details": {"reasoning_tokens": 96}}, "ttft_s": 14.42599186499865, "elapsed_s": 15.14422588799789, "decode_tps": 160.11494348287312, "max_stream_gap_s": 0.01879984400147805, "events": 41, "sha256": "e054eb4577e203d59776c06555ff8dff56d50e49389606fa8a7344884f985155"}
{"name": "long-context-1", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 125995, "total_tokens": 126114, "completion_tokens": 119, "completion_tokens_details": {"reasoning_tokens": 99}}, "ttft_s": 0.7020562550023897, "elapsed_s": 1.4927438169979723, "decode_tps": 149.23720274818137, "max_stream_gap_s": 0.01888078500633128, "events": 45, "sha256": "109b3120d1bf2f56bd0c1ab331e7692f8a0a37b091eb2adb8d7a0a54731dba54"}
{"name": "long-context-2", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 125995, "total_tokens": 126114, "completion_tokens": 119, "completion_tokens_details": {"reasoning_tokens": 99}}, "ttft_s": 0.7015097360053915, "elapsed_s": 1.4736580300013884, "decode_tps": 152.82038556263618, "max_stream_gap_s": 0.018826871004421264, "events": 44, "sha256": "1275326ebe3452473a77c76ba9ec5b91f06f8896ffd6de203abf1f9129842a90"}
{"name": "long-context-image", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 111670, "total_tokens": 111902, "completion_tokens": 232, "completion_tokens_details": {"reasoning_tokens": 187}}, "ttft_s": 12.815331379999407, "elapsed_s": 14.372689276002347, "decode_tps": 148.32813998174495, "max_stream_gap_s": 0.01881139999750303, "events": 87, "sha256": "4b7c8fb1d0d992dda6a5a680074a3aa037b1c33fd732b7315720e712693c2335"}
{"name": "queued-0", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 55, "total_tokens": 119, "completion_tokens": 64, "completion_tokens_details": {"reasoning_tokens": 58}}, "ttft_s": 0.08533696200174745, "elapsed_s": 0.4814725750038633, "decode_tps": 159.0364459346489, "max_stream_gap_s": 0.018437628001265693, "events": 22, "sha256": "c775e82fbe7367311970d698f4880b3e86da93aa21640d45d95ee9475e335166"}
{"name": "queued-1", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 55, "total_tokens": 98, "completion_tokens": 43, "completion_tokens_details": {"reasoning_tokens": 37}}, "ttft_s": 0.5489882670008228, "elapsed_s": 0.8192126439971616, "decode_tps": 155.42639219617496, "max_stream_gap_s": 0.018371916994510684, "events": 15, "sha256": "577bfda055d6b1f136ea30fd3c42b3954036dd654d2eb7cace48396c49aa115a"}
{"name": "queued-2", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 55, "total_tokens": 119, "completion_tokens": 64, "completion_tokens_details": {"reasoning_tokens": 58}}, "ttft_s": 0.8859058559974073, "elapsed_s": 1.2823282210010802, "decode_tps": 158.92140696808642, "max_stream_gap_s": 0.018409249001706485, "events": 22, "sha256": "4e0dac459752edb516d9c610865ec672d6805ddc71af097d21b28f7c53179b47"}
{"name": "queued-3", "passed": true, "finish": "stop", "usage": {"prompt_tokens": 55, "total_tokens": 119, "completion_tokens": 64, "completion_tokens_details": {"reasoning_tokens": 58}}, "ttft_s": 1.3495687850008835, "elapsed_s": 1.743830876002903, "decode_tps": 159.79218250449873, "max_stream_gap_s": 0.018336048000492156, "events": 23, "sha256": "fbb92f72869a68308179711e06612346b886a880c1f5fbd390eb0731790dbd0c"}
SUITE_COMPLETE
audit/tuning/steps-123/mtp2-b2048/server.log
+730
View File
@@ -0,0 +1,730 @@
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:347]
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:347] █ █ █▄ ▄█
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:347] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.3.1.dev3+g0bfc7a15d
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:347] █▄█▀ █ █ █ █ model /model
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:347] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:347]
(APIServer pid=1) INFO 09-18 14:14:09 [api_utils.py:286] non-default args: {'model_tag': '/model', 'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_xml', 'host': '0.0.0.0', 'api_key': '***', 'model': '/model', 'dtype': 'bfloat16', 'max_model_len': 131072, 'served_model_name': ['qwen3.8-flash-next'], 'load_format': 'safetensors', 'reasoning_parser': 'qwen3', 'gpu_memory_utilization': 0.985, 'kv_cache_dtype': 'fp8', 'enable_prefix_caching': True, 'max_num_batched_tokens': 2048, 'max_num_seqs': 1, 'enable_chunked_prefill': True, 'enable_flashinfer_autotune': False, 'speculative_config': {'method': 'mtp', 'num_speculative_tokens': 2}, 'compilation_config': {'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': [], 'ir_enable_torch_wrap': None, 'splitting_ops': None, 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': None, 'compile_ranges_endpoints': None, 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL: 2>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': [1, 3], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': None, 'pass_config': {}, 'max_cudagraph_capture_size': None, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': None, 'static_all_moe_layers': []}, 'engram_config': EngramConfig(cpu_offload=True, embedding_across_dp=False, dp_shared_memory=False)}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) INFO 09-18 14:14:09 [model.py:691] Resolved architecture: Qwen4ExpForConditionalGeneration
(APIServer pid=1) INFO 09-18 14:14:09 [model.py:2024] Using max model len 131072
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) INFO 09-18 14:14:13 [cache.py:345] Using fp8 data type to store kv cache. It reduces the GPU memory footprint and boosts the performance. Meanwhile, it may cause accuracy drop without a proper scaling factor
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) INFO 09-18 14:14:13 [model.py:691] Resolved architecture: Qwen4ExpMTP
(APIServer pid=1) INFO 09-18 14:14:13 [model.py:2024] Using max model len 262144
(APIServer pid=1) WARNING 09-18 14:14:13 [speculative.py:1360] Enabling num_speculative_tokens > 1 will run multiple times of forward on same MTP layer,which may result in lower acceptance rate
(APIServer pid=1) INFO 09-18 14:14:13 [speculative.py:1653] Overriding draft model max model len from 262144 to 131072
(APIServer pid=1) INFO 09-18 14:14:13 [config.py:625] Mamba cache mode is set to 'align' for Qwen4ExpForConditionalGeneration by default when prefix caching is enabled
(APIServer pid=1) INFO 09-18 14:14:13 [vllm.py:1271] Resolved Engram configuration: EngramConfig(cpu_offload=True, embedding_across_dp=False, dp_shared_memory=False)
(APIServer pid=1) INFO 09-18 14:14:13 [vllm.py:781] Auto-enabling VLLM_USE_BREAKABLE_CUDAGRAPH=1. Set VLLM_USE_BREAKABLE_CUDAGRAPH=0 to opt out.
(APIServer pid=1) INFO 09-18 14:14:13 [kernel.py:408] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native'], gelu_and_mul_sparse=['triton', 'native'])
(APIServer pid=1) WARNING 09-18 14:14:13 [vllm.py:2152] max_num_scheduled_tokens is set to 2048 based on the speculative decoding settings. This may lead to suboptimal performance. Consider increasing max_num_batched_tokens to accommodate the additional draft token slots, or decrease num_speculative_tokens.
(APIServer pid=1) INFO 09-18 14:14:13 [compilation.py:331] Enabled custom fusions: norm_quant, act_quant
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] The `use_fast` parameter is deprecated and will be removed in a future version. Use `backend="torchvision"` instead of `use_fast=True`, or `backend="pil"` instead of `use_fast=False`.
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(EngineCore pid=113) INFO 09-18 14:14:25 [core.py:123] Initializing a V1 LLM engine (v0.3.1.dev3+g0bfc7a15d) with config: model='/model', speculative_config=SpeculativeConfig(method='mtp', model='/model', num_spec_tokens=2), tokenizer='/model', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=131072, download_dir=None, load_format=safetensors, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=modelopt_mixed, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=fp8, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, per_request_spec_decode_metrics='none', kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False, jit_monitor_mode='warn', jit_monitor_verbose=False), seed=0, served_model_name=qwen3.8-flash-next, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.NONE: 0>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['+quant_fp8', 'all', '+quant_fp8'], 'ir_enable_torch_wrap': False, 'splitting_ops': [], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL: 2>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 3], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': True, 'fuse_act_quant': True, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'enable_qk_norm_rope_fusion': False, 'fuse_rope_kvcache_cat_mla': False, 'fuse_act_padding': False, 'fuse_qk_norm_rope_kvcache': False}, 'max_cudagraph_capture_size': 3, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}, kernel_config=KernelConfig(ir_op_priority=IrOpPriorityConfig(rms_norm=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native'], gelu_and_mul_sparse=['triton', 'native']), enable_flashinfer_autotune=False, enable_cutedsl_warmup=True, enable_jit_warmup=True, moe_backend='auto', sparse_indexer_topk_backend='auto', linear_backend='auto', linear_backend_per_quant=None)
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(EngineCore pid=113) INFO 09-18 14:14:26 [parallel_state.py:1825] world_size=1 rank=0 local_rank=0 distributed_init_method=file:///tmp/vllm_dist_ed11f4f25e124a16965c184de0adfebf backend=nccl
(EngineCore pid=113) INFO 09-18 14:14:26 [parallel_state.py:2269] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, ETP rank 0, EP rank 0, EPLB rank N/A
(EngineCore pid=113) INFO 09-18 14:14:26 [gpu_worker.py:441] Using V2 Model Runner
(EngineCore pid=113) INFO 09-18 14:14:27 [model_runner.py:387] Loading model from scratch...
(EngineCore pid=113) INFO 09-18 14:14:27 [cuda.py:595] Using backend AttentionBackendEnum.FLASH_ATTN for vit attention
(EngineCore pid=113) INFO 09-18 14:14:27 [mm_encoder_attention.py:372] Using AttentionBackendEnum.FLASH_ATTN for MMEncoderAttention.
(EngineCore pid=113) INFO 09-18 14:14:27 [qwen_gdn_linear_attn.py:176] Using FlashInfer GDN prefill kernel (requested=auto, head_k_dim=128).
(EngineCore pid=113) INFO 09-18 14:14:27 [qwen_gdn_linear_attn.py:528] GDN decode kernel: cuda
(EngineCore pid=113) INFO 09-18 14:14:29 [nvfp4.py:302] Using 'FLASHINFER_CUTLASS' NvFp4 MoE backend out of potential backends: ['FLASHINFER_TRTLLM', 'FLASHINFER_CUTEDSL', 'FLASHINFER_CUTEDSL_BATCHED', 'FLASHINFER_CUTLASS', 'VLLM_CUTLASS', 'MARLIN', 'HUMMING', 'EMULATION'].
(APIServer pid=1) [transformers] Qwen3VL video processing does not apply the per-frame pixel cap the reference implementation (qwen-vl-utils) applies, so some videos cost far more tokens than they would there. In v5.22 the capped behavior will become the default and `cap_pixels_per_frame` will be removed. Pass `cap_pixels_per_frame=True` to adopt the reference behavior now, or `False` to keep the current behavior and silence this warning.
(APIServer pid=1) INFO 09-18 14:14:31 [base.py:261] Multi-modal warmup completed in 12.320s
(APIServer pid=1) INFO 09-18 14:14:33 [base.py:261] Readonly multi-modal warmup completed in 1.302s
(EngineCore pid=113) INFO 09-18 14:15:03 [ngram_embedding.py:720] Initialized PLE embedding language_model.model.layers.1.ple.ple_embedding.ngram_embedding: quantization_method=Qwen4ExpPLEFp8EmbeddingMethod, weight_dtype=torch.float8_e4m3fn, weight_device=cpu, pinned=True
(EngineCore pid=113) INFO 09-18 14:15:03 [flash_attn.py:1115] Using FlashAttention version 2
(EngineCore pid=113) WARNING 09-18 14:15:03 [compilation.py:1350] Op 'quant_fp8' not present in model, enabling with '+quant_fp8' has no effect
(EngineCore pid=113) INFO 09-18 14:15:03 [weight_utils.py:900] Filesystem type for checkpoints: EXT4. Checkpoint size: 123.57 GiB. Available RAM: 142.31 GiB.
(EngineCore pid=113) INFO 09-18 14:15:03 [weight_utils.py:923] Auto-prefetch is disabled because the filesystem (EXT4) is not a recognized network FS (NFS/Lustre). If you want to force prefetching, start vLLM with --safetensors-load-strategy=prefetch.
(EngineCore pid=113)
Loading safetensors checkpoint shards: 0% Completed | 0/11 [00:00<?, ?it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 9% Completed | 1/11 [00:01<00:16, 1.63s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 18% Completed | 2/11 [00:06<00:33, 3.74s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 27% Completed | 3/11 [00:12<00:36, 4.52s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 36% Completed | 4/11 [00:17<00:34, 4.87s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 45% Completed | 5/11 [00:23<00:30, 5.11s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 55% Completed | 6/11 [00:28<00:26, 5.26s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 64% Completed | 7/11 [00:34<00:21, 5.36s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 73% Completed | 8/11 [00:40<00:16, 5.47s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 82% Completed | 9/11 [00:41<00:08, 4.20s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:42<00:00, 2.38s/it]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:42<00:00, 3.83s/it]
(EngineCore pid=113)
(EngineCore pid=113) INFO 09-18 14:15:45 [default_loader.py:430] Loading weights took 42.29 seconds
(EngineCore pid=113) INFO 09-18 14:15:45 [nvfp4.py:611] Using MoEPrepareAndFinalizeNoDPEPModular
(EngineCore pid=113) INFO 09-18 14:15:46 [vllm.py:1271] Resolved Engram configuration: EngramConfig(cpu_offload=True, embedding_across_dp=False, dp_shared_memory=False)
(EngineCore pid=113) INFO 09-18 14:15:46 [kernel.py:408] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native'], gelu_and_mul_sparse=['triton', 'native'])
(EngineCore pid=113) WARNING 09-18 14:15:46 [vllm.py:2152] max_num_scheduled_tokens is set to 2048 based on the speculative decoding settings. This may lead to suboptimal performance. Consider increasing max_num_batched_tokens to accommodate the additional draft token slots, or decrease num_speculative_tokens.
(EngineCore pid=113) INFO 09-18 14:15:46 [compilation.py:331] Enabled custom fusions: norm_quant, act_quant
(EngineCore pid=113) INFO 09-18 14:15:46 [fp8.py:433] Using DEEPGEMM Fp8 MoE backend out of potential backends: ['AITER', 'FLASHINFER_TRTLLM', 'FLASHINFER_CUTLASS', 'DEEPGEMM', 'TRITON', 'MARLIN', 'HUMMING', 'BATCHED_DEEPGEMM', 'BATCHED_TRITON', 'XPU', 'CPU', 'HPC'].
(EngineCore pid=113) INFO 09-18 14:15:47 [weight_utils.py:900] Filesystem type for checkpoints: EXT4. Checkpoint size: 123.57 GiB. Available RAM: 142.17 GiB.
(EngineCore pid=113)
Loading safetensors checkpoint shards: 0% Completed | 0/11 [00:00<?, ?it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 18% Completed | 2/11 [00:00<00:01, 5.13it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 27% Completed | 3/11 [00:00<00:01, 4.03it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 36% Completed | 4/11 [00:01<00:01, 3.63it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 45% Completed | 5/11 [00:01<00:01, 3.41it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 55% Completed | 6/11 [00:01<00:01, 3.30it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 64% Completed | 7/11 [00:02<00:01, 3.24it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 73% Completed | 8/11 [00:02<00:00, 3.19it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 82% Completed | 9/11 [00:02<00:00, 3.69it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:02<00:00, 3.89it/s]
(EngineCore pid=113)
Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:02<00:00, 3.68it/s]
(EngineCore pid=113)
(EngineCore pid=113) INFO 09-18 14:15:50 [default_loader.py:430] Loading weights took 3.00 seconds
(EngineCore pid=113) INFO 09-18 14:15:50 [deep_gemm.py:196] deep_gemm not found in site-packages, trying vendored vllm.third_party.deep_gemm
(EngineCore pid=113) INFO 09-18 14:15:50 [deep_gemm.py:223] DeepGEMM PDL enabled on vllm.third_party.deep_gemm.
(EngineCore pid=113) INFO 09-18 14:15:50 [deep_gemm.py:136] DeepGEMM E8M0 enabled on current platform.
(EngineCore pid=113) INFO 09-18 14:15:52 [fp8.py:733] Using MoEPrepareAndFinalizeNoDPEPModular
(EngineCore pid=113) WARNING 09-18 14:15:52 [speculator.py:235] Draft model Qwen4ExpMTP does not support external multimodal embeddings. Embeddings from the target model will not be passed to the drafter; using text-only draft inputs instead.
(EngineCore pid=113) INFO 09-18 14:15:53 [model_runner.py:419] Model loading took 76.36 GiB memory and 86.461433 seconds
(EngineCore pid=113) INFO 09-18 14:15:53 [topk_topp_sampler.py:78] Using FlashInfer for top-p & top-k sampling.
(EngineCore pid=113) INFO 09-18 14:15:53 [interface.py:918] Setting attention block size to 3184 tokens to ensure that attention page size is >= mamba page size.
(EngineCore pid=113) INFO 09-18 14:15:53 [interface.py:942] Padding mamba page size by 0.38% to ensure that mamba page size and attention page size are exactly equal.
(EngineCore pid=113) INFO 09-18 14:15:53 [utils.py:320] Using BLNHC KV cache layout.
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] The `use_fast` parameter is deprecated and will be removed in a future version. Use `backend="torchvision"` instead of `use_fast=True`, or `backend="pil"` instead of `use_fast=False`.
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
(EngineCore pid=113) INFO 09-18 14:15:58 [encoder_runner.py:131] Encoder cache will be initialized with a budget of 16384 tokens, and profiled with 1 image items of the maximum feature size.
(EngineCore pid=113) WARNING 09-18 14:16:20 [kv_cache_utils.py:2219] Speculative decoding (method=mtp) is enabled but no KV cache group could be identified as the draft model's.
(EngineCore pid=113) WARNING 09-18 14:16:20 [compilation.py:1415] CUDAGraphMode.FULL is not supported with GDNAttentionBackend backend (support: AttentionCGSupport.UNIFORM_BATCH); setting cudagraph_mode=FULL_DECODE_ONLY
(EngineCore pid=113) INFO 09-18 14:16:20 [speculator.py:119] Fused multi-step draft decode is not supported by attention backend(s) QWEN4_EXP_EXP_QSA_STATE; falling back to rebuilding attention metadata between draft steps.
(EngineCore pid=113)
Capturing CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing CUDA graphs (FULL): 100%|██████████| 1/1 [00:01<00:00, 1.83s/it]
Capturing CUDA graphs (FULL): 100%|██████████| 1/1 [00:01<00:00, 1.83s/it]
(EngineCore pid=113) INFO 09-18 14:16:22 [speculator.py:150] Capturing model for speculator...
(EngineCore pid=113)
Capturing prefill CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing prefill CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 2.17it/s]
Capturing prefill CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 2.17it/s]
(EngineCore pid=113)
Capturing decode CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing decode CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 5.69it/s]
Capturing decode CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 5.69it/s]
(EngineCore pid=113) INFO 09-18 14:16:23 [model_runner.py:1057] Graph capturing finished in 3 secs, took 0.14 GiB
(EngineCore pid=113) INFO 09-18 14:16:24 [gpu_worker.py:641] Available KV cache memory: 2.78 GiB
(EngineCore pid=113) INFO 09-18 14:16:24 [gpu_worker.py:656] CUDA graph memory profiling is enabled (default since v0.21.0). The current --gpu-memory-utilization=0.9850 is equivalent to --gpu-memory-utilization=0.9833 without CUDA graph memory profiling. To maintain the same effective KV cache size as before, increase --gpu-memory-utilization to 0.9867. To disable, set VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0.
(EngineCore pid=113) WARNING 09-18 14:16:24 [kv_cache_utils.py:2219] Speculative decoding (method=mtp) is enabled but no KV cache group could be identified as the draft model's.
(EngineCore pid=113) INFO 09-18 14:16:24 [kv_cache_utils.py:2404] GPU KV cache size: 146,622 tokens, Maximum concurrency for 131,072 tokens per request: 1.12x
(EngineCore pid=113) INFO 09-18 14:16:24 [kernel_warmup.py:171] JIT kernel warmup starting.
(EngineCore pid=113) INFO 09-18 14:16:24 [kernel_warmup.py:184] JIT kernel warmup finished in 0.00s.
(EngineCore pid=113) INFO 09-18 14:16:24 [qwen_vl_triton_warmup.py:57] Warmed position embedding and vision rotary kernels on grids=[(1, 16, 16), (1, 16, 2), (1, 2, 16), (1, 2, 2)].
(EngineCore pid=113) INFO 09-18 14:16:24 [qwen_vl_triton_warmup.py:98] Warmed M-RoPE Triton kernels.
(EngineCore pid=113) INFO 09-18 14:16:24 [mamba_triton_warmup.py:42] Warmed Mamba batch_memcpy_kernel.
(EngineCore pid=113) INFO 09-18 14:16:25 [qwen4_exp_qsa_warmup.py:71] Warmed up Qwen4Exp QSA decode kernels: ((1, 1), (2, 1), (3, 1)).
(EngineCore pid=113) INFO 09-18 14:16:30 [qwen4_exp_qsa_warmup.py:85] Warmed up Qwen4Exp QSA sparse attention kernels: ((32, 2, 1), (32, 4, 4), (64, 1, 2), (64, 4, 4), (64, 8, 4), (64, 33, 8), (128, 4, 4), (128, 8, 4)).
(EngineCore pid=113) INFO 09-18 14:16:30 [kernel_warmup.py:254] Skipping FlashInfer autotune because it is disabled.
(EngineCore pid=113)
Capturing CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 9.91it/s]
Capturing CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 9.89it/s]
(EngineCore pid=113) INFO 09-18 14:16:39 [speculator.py:150] Capturing model for speculator...
(EngineCore pid=113)
Capturing prefill CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing prefill CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 118.66it/s]
(EngineCore pid=113)
Capturing decode CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing decode CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 176.98it/s]
(EngineCore pid=113) INFO 09-18 14:16:39 [model_runner.py:1057] Graph capturing finished in 1 secs, took 0.13 GiB
(EngineCore pid=113) INFO 09-18 14:16:39 [gpu_worker.py:824] CUDA graph pool memory: 0.13 GiB (actual), 0.14 GiB (estimated), difference: 0.01 GiB (5.8%).
(EngineCore pid=113) INFO 09-18 14:16:39 [gpu_worker.py:887] Free memory on device (82.59/83.05 GiB) on startup. Desired GPU memory utilization is (0.985, 81.8 GiB). Actual usage is 77.85 GiB for consumed memory (weights + non-torch), 1.17 GiB for peak activation, and 0.13 GiB for CUDAGraph memory. Replace gpu_memory_utilization config with `--kv-cache-memory=2685284312` (2.5 GiB) to fit into requested memory, or `--kv-cache-memory=3531951104` (3.29 GiB) to fully utilize gpu memory. Current kv cache memory in use is 2.78 GiB.
(EngineCore pid=113) INFO 09-18 14:16:40 [jit_monitor.py:84] Kernel JIT monitor activated; monitored JIT compilations during inference will use mode=warn.
(EngineCore pid=113) WARNING 09-18 14:16:41 [torch_utils.py:274] OMP_NUM_THREADS=8 is set; leaving Torch threads at 8 for serving. Multi-threaded torch CPU ops during serving can degrade performance through spin-wait contention and cgroup CPU-quota throttling.
(EngineCore pid=113) INFO 09-18 14:16:41 [core.py:380] init engine (profile, create kv cache, warmup model) took 47.40 s
(EngineCore pid=113) INFO 09-18 14:16:41 [kv_cache_utils.py:762] kv cache group sizes [3184, 3184, 3184, 3184, 8, 3184]
(EngineCore pid=113) INFO 09-18 14:16:41 [kv_cache_utils.py:763] kv lcm block sizes 3184
(EngineCore pid=113) INFO 09-18 14:16:41 [kernel.py:408] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['vllm_c', 'native'], fused_add_rms_norm=['vllm_c', 'native'], gelu_and_mul_sparse=['triton', 'native'])
(APIServer pid=1) INFO 09-18 14:16:41 [entry.py:132] Supported tasks: ['generate']
(APIServer pid=1) INFO 09-18 14:16:41 [factories.py:76] Scale-out endpoints are disabled. Set --enable-scale-out to enable them.
(APIServer pid=1) INFO 09-18 14:16:41 [parser_manager.py:34] "auto" tool choice has been enabled.
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
(APIServer pid=1) INFO 09-18 14:16:41 [hf.py:642] Detected the chat template content format to be 'openai'. You can set `--chat-template-content-format` to override this.
(APIServer pid=1) WARNING 09-18 14:16:41 [model.py:1769] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 1.0, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(APIServer pid=1) INFO 09-18 14:16:41 [entry.py:136] Starting vLLM server on http://0.0.0.0:8000
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:60] Available routes are:
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /openapi.json, Methods: HEAD, GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /docs, Methods: HEAD, GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /docs/oauth2-redirect, Methods: HEAD, GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /redoc, Methods: HEAD, GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /load, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /version, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /health, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /metrics, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /tokenize, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /detokenize, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/models, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /ping, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /ping, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /invocations, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/chat/completions, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/chat/completions/batch, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/responses, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/responses/{response_id}, Methods: GET
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/responses/{response_id}/cancel, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/completions, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/messages, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /v1/messages/count_tokens, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /generative_scoring, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /scale_elastic_ep, Methods: POST
(APIServer pid=1) INFO 09-18 14:16:41 [launcher.py:69] Route: /is_scaling_elastic_ep, Methods: POST
(APIServer pid=1) INFO: Started server process [1]
(APIServer pid=1) INFO: Waiting for application startup.
(APIServer pid=1) INFO: Application startup complete.
(APIServer pid=1) INFO: 127.0.0.1:52136 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36256 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36262 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(EngineCore pid=113) WARNING 09-18 14:16:46 [jit_monitor.py:140] Triton kernel JIT compilation during inference: layer_norm_fwd_kernel. This causes a latency spike; consider extending warmup to cover this shape/config.
(EngineCore pid=113) WARNING 09-18 14:16:46 [jit_monitor.py:140] Triton kernel JIT compilation during inference: _count_expert_num_tokens. This causes a latency spike; consider extending warmup to cover this shape/config.
(EngineCore pid=113) WARNING 09-18 14:16:46 [jit_monitor.py:140] Triton kernel JIT compilation during inference: _compute_local_logits_stats_kernel. This causes a latency spike; consider extending warmup to cover this shape/config.
(EngineCore pid=113) WARNING 09-18 14:16:46 [jit_monitor.py:140] Triton kernel JIT compilation during inference: _rejection_kernel. This causes a latency spike; consider extending warmup to cover this shape/config.
(EngineCore pid=113) WARNING 09-18 14:16:47 [jit_monitor.py:140] Triton kernel JIT compilation during inference: _resample_kernel. This causes a latency spike; consider extending warmup to cover this shape/config.
(APIServer pid=1) INFO: 172.21.0.1:36278 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36282 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36290 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36304 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36306 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36310 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36316 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36332 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36342 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36352 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:16:52 [loggers.py:323] Engine 000: Avg prompt throughput: 53.5 tokens/s, Avg generation throughput: 60.9 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=1) INFO 09-18 14:16:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.91, Accepted throughput: 39.90 tokens/s, Drafted throughput: 41.72 tokens/s, Accepted: 440 tokens, Drafted: 460 tokens, Per-position acceptance rate: 0.987, 0.926, Avg Draft acceptance rate: 95.7%
(APIServer pid=1) INFO: 172.21.0.1:36364 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36378 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:36380 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:33586 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:33600 - "POST /v1/chat/completions HTTP/1.1" 200 OK
[rank0]:[W918 14:16:56.003832297 CUDACachingAllocator.cpp:3933] memory allocation failed with OOM on device 0 while trying to allocate 377487360 bytes (free: 64946176, total: 89173131264).
(APIServer pid=1) INFO: 172.21.0.1:33614 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:33630 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:17:02 [loggers.py:323] Engine 000: Avg prompt throughput: 2790.6 tokens/s, Avg generation throughput: 72.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:17:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.72, Accepted throughput: 45.70 tokens/s, Drafted throughput: 53.00 tokens/s, Accepted: 457 tokens, Drafted: 530 tokens, Per-position acceptance rate: 0.925, 0.800, Avg Draft acceptance rate: 86.2%
(APIServer pid=1) INFO: 172.21.0.1:33642 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:17:12 [loggers.py:323] Engine 000: Avg prompt throughput: 7.7 tokens/s, Avg generation throughput: 124.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:17:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.27, Accepted throughput: 69.90 tokens/s, Drafted throughput: 110.19 tokens/s, Accepted: 699 tokens, Drafted: 1102 tokens, Per-position acceptance rate: 0.737, 0.532, Avg Draft acceptance rate: 63.4%
(APIServer pid=1) INFO: 127.0.0.1:35366 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43852 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:17:22 [loggers.py:323] Engine 000: Avg prompt throughput: 7.7 tokens/s, Avg generation throughput: 118.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:17:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.14, Accepted throughput: 62.90 tokens/s, Drafted throughput: 110.40 tokens/s, Accepted: 629 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.707, 0.433, Avg Draft acceptance rate: 57.0%
(APIServer pid=1) INFO 09-18 14:17:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 128.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:17:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.30, Accepted throughput: 72.60 tokens/s, Drafted throughput: 111.60 tokens/s, Accepted: 726 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.758, 0.543, Avg Draft acceptance rate: 65.1%
(APIServer pid=1) INFO: 172.21.0.1:44946 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:17:42 [loggers.py:323] Engine 000: Avg prompt throughput: 7.7 tokens/s, Avg generation throughput: 119.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:17:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 64.09 tokens/s, Drafted throughput: 110.38 tokens/s, Accepted: 641 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.707, 0.455, Avg Draft acceptance rate: 58.1%
(APIServer pid=1) INFO: 127.0.0.1:40726 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:17:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 123.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:17:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.22, Accepted throughput: 68.10 tokens/s, Drafted throughput: 111.40 tokens/s, Accepted: 681 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.727, 0.496, Avg Draft acceptance rate: 61.1%
(APIServer pid=1) INFO: 172.21.0.1:41494 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:51114 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:18:02 [loggers.py:323] Engine 000: Avg prompt throughput: 15.8 tokens/s, Avg generation throughput: 124.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:18:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.27, Accepted throughput: 69.80 tokens/s, Drafted throughput: 109.80 tokens/s, Accepted: 698 tokens, Drafted: 1098 tokens, Per-position acceptance rate: 0.754, 0.517, Avg Draft acceptance rate: 63.6%
(APIServer pid=1) INFO: 172.21.0.1:53922 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:18:12 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 129.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:18:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.32, Accepted throughput: 73.50 tokens/s, Drafted throughput: 111.00 tokens/s, Accepted: 735 tokens, Drafted: 1110 tokens, Per-position acceptance rate: 0.766, 0.559, Avg Draft acceptance rate: 66.2%
(APIServer pid=1) INFO: 127.0.0.1:57802 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:18:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 127.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:18:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.28, Accepted throughput: 71.50 tokens/s, Drafted throughput: 111.80 tokens/s, Accepted: 715 tokens, Drafted: 1118 tokens, Per-position acceptance rate: 0.758, 0.521, Avg Draft acceptance rate: 64.0%
(APIServer pid=1) INFO: 172.21.0.1:36444 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:18:32 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 128.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:18:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.31, Accepted throughput: 72.70 tokens/s, Drafted throughput: 110.80 tokens/s, Accepted: 727 tokens, Drafted: 1108 tokens, Per-position acceptance rate: 0.765, 0.547, Avg Draft acceptance rate: 65.6%
(APIServer pid=1) INFO 09-18 14:18:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 129.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:18:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.32, Accepted throughput: 73.70 tokens/s, Drafted throughput: 111.79 tokens/s, Accepted: 737 tokens, Drafted: 1118 tokens, Per-position acceptance rate: 0.764, 0.555, Avg Draft acceptance rate: 65.9%
(APIServer pid=1) INFO: 172.21.0.1:38818 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:34668 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:40728 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:18:52 [loggers.py:323] Engine 000: Avg prompt throughput: 15.8 tokens/s, Avg generation throughput: 120.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:18:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.20, Accepted throughput: 65.80 tokens/s, Drafted throughput: 109.99 tokens/s, Accepted: 658 tokens, Drafted: 1100 tokens, Per-position acceptance rate: 0.709, 0.487, Avg Draft acceptance rate: 59.8%
(APIServer pid=1) INFO 09-18 14:19:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 122.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:19:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.20, Accepted throughput: 67.00 tokens/s, Drafted throughput: 111.40 tokens/s, Accepted: 670 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.716, 0.487, Avg Draft acceptance rate: 60.1%
(APIServer pid=1) INFO: 172.21.0.1:50984 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:19:12 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 119.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:19:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 64.20 tokens/s, Drafted throughput: 110.80 tokens/s, Accepted: 642 tokens, Drafted: 1108 tokens, Per-position acceptance rate: 0.702, 0.457, Avg Draft acceptance rate: 57.9%
(APIServer pid=1) INFO: 127.0.0.1:57380 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:37540 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:19:22 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 122.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:19:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.22, Accepted throughput: 67.59 tokens/s, Drafted throughput: 110.59 tokens/s, Accepted: 676 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.714, 0.508, Avg Draft acceptance rate: 61.1%
(APIServer pid=1) INFO 09-18 14:19:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 121.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:19:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.17, Accepted throughput: 65.50 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 655 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.710, 0.464, Avg Draft acceptance rate: 58.7%
(APIServer pid=1) INFO: 172.21.0.1:43060 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:19:42 [loggers.py:323] Engine 000: Avg prompt throughput: 7.5 tokens/s, Avg generation throughput: 124.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:19:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.26, Accepted throughput: 69.60 tokens/s, Drafted throughput: 110.60 tokens/s, Accepted: 696 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.741, 0.517, Avg Draft acceptance rate: 62.9%
(APIServer pid=1) INFO: 127.0.0.1:45568 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:19:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 137.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:19:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.47, Accepted throughput: 81.90 tokens/s, Drafted throughput: 111.20 tokens/s, Accepted: 819 tokens, Drafted: 1112 tokens, Per-position acceptance rate: 0.831, 0.642, Avg Draft acceptance rate: 73.7%
(APIServer pid=1) INFO 09-18 14:20:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 150.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 23.1%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:20:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.71, Accepted throughput: 95.00 tokens/s, Drafted throughput: 110.80 tokens/s, Accepted: 950 tokens, Drafted: 1108 tokens, Per-position acceptance rate: 0.919, 0.796, Avg Draft acceptance rate: 85.7%
(APIServer pid=1) INFO 09-18 14:20:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 145.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 23.1%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:20:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.63, Accepted throughput: 90.20 tokens/s, Drafted throughput: 110.79 tokens/s, Accepted: 902 tokens, Drafted: 1108 tokens, Per-position acceptance rate: 0.888, 0.740, Avg Draft acceptance rate: 81.4%
(APIServer pid=1) INFO: 127.0.0.1:41446 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:20:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 138.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 24.6%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:20:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.51, Accepted throughput: 83.29 tokens/s, Drafted throughput: 110.59 tokens/s, Accepted: 833 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.837, 0.669, Avg Draft acceptance rate: 75.3%
(APIServer pid=1) INFO 09-18 14:20:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 134.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 24.6%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:20:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.43, Accepted throughput: 79.10 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 791 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.813, 0.620, Avg Draft acceptance rate: 71.6%
(APIServer pid=1) INFO 09-18 14:20:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 134.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 24.6%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:20:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.45, Accepted throughput: 79.80 tokens/s, Drafted throughput: 110.19 tokens/s, Accepted: 798 tokens, Drafted: 1102 tokens, Per-position acceptance rate: 0.815, 0.633, Avg Draft acceptance rate: 72.4%
(APIServer pid=1) INFO: 127.0.0.1:38588 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:20:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 131.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 26.2%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:20:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.43, Accepted throughput: 77.00 tokens/s, Drafted throughput: 108.00 tokens/s, Accepted: 770 tokens, Drafted: 1080 tokens, Per-position acceptance rate: 0.743, 0.683, Avg Draft acceptance rate: 71.3%
(APIServer pid=1) INFO 09-18 14:21:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 154.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 26.2%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:21:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.88, Accepted throughput: 100.70 tokens/s, Drafted throughput: 107.40 tokens/s, Accepted: 1007 tokens, Drafted: 1074 tokens, Per-position acceptance rate: 0.952, 0.924, Avg Draft acceptance rate: 93.8%
(APIServer pid=1) INFO 09-18 14:21:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 143.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 27.7%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:21:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.66, Accepted throughput: 89.40 tokens/s, Drafted throughput: 108.00 tokens/s, Accepted: 894 tokens, Drafted: 1080 tokens, Per-position acceptance rate: 0.833, 0.822, Avg Draft acceptance rate: 82.8%
(APIServer pid=1) INFO: 127.0.0.1:42148 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:21:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 151.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 27.7%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:21:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.80, Accepted throughput: 97.59 tokens/s, Drafted throughput: 108.19 tokens/s, Accepted: 976 tokens, Drafted: 1082 tokens, Per-position acceptance rate: 0.906, 0.898, Avg Draft acceptance rate: 90.2%
(APIServer pid=1) [transformers] Token indices sequence length is longer than the specified maximum sequence length for this model (268298 > 262144). Running this sequence through the model will result in indexing errors
(APIServer pid=1) INFO: 172.21.0.1:48854 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48862 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48874 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48886 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48894 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48902 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48914 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:21:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 140.5 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO 09-18 14:21:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.86, Accepted throughput: 91.39 tokens/s, Drafted throughput: 98.39 tokens/s, Accepted: 914 tokens, Drafted: 984 tokens, Per-position acceptance rate: 0.929, 0.929, Avg Draft acceptance rate: 92.9%
(APIServer pid=1) INFO: 172.21.0.1:48926 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48928 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48934 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48948 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48950 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48964 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48968 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48976 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:21:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 67.7%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
(APIServer pid=1) INFO: 127.0.0.1:49396 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:38790 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:38796 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:38802 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:21:52 [loggers.py:323] Engine 000: Avg prompt throughput: 13599.9 tokens/s, Avg generation throughput: 37.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 32.3%, Prefix cache hit rate: 46.6%, MM cache hit rate: 71.4%
(APIServer pid=1) INFO 09-18 14:21:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.80, Accepted throughput: 11.95 tokens/s, Drafted throughput: 13.30 tokens/s, Accepted: 239 tokens, Drafted: 266 tokens, Per-position acceptance rate: 0.940, 0.857, Avg Draft acceptance rate: 89.8%
(APIServer pid=1) INFO 09-18 14:22:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 73.8%, Prefix cache hit rate: 46.6%, MM cache hit rate: 71.4%
(APIServer pid=1) INFO: 172.21.0.1:43834 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43840 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43848 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43858 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43874 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43878 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:43890 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:22:12 [loggers.py:323] Engine 000: Avg prompt throughput: 13594.6 tokens/s, Avg generation throughput: 70.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 23.1%, Prefix cache hit rate: 52.5%, MM cache hit rate: 77.8%
(APIServer pid=1) INFO 09-18 14:22:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.77, Accepted throughput: 22.55 tokens/s, Drafted throughput: 25.50 tokens/s, Accepted: 451 tokens, Drafted: 510 tokens, Per-position acceptance rate: 0.929, 0.839, Avg Draft acceptance rate: 88.4%
(APIServer pid=1) INFO: 172.21.0.1:51984 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:58388 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:22:22 [loggers.py:323] Engine 000: Avg prompt throughput: 1215.2 tokens/s, Avg generation throughput: 113.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 52.5%, MM cache hit rate: 77.8%
(APIServer pid=1) INFO 09-18 14:22:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.29, Accepted throughput: 63.79 tokens/s, Drafted throughput: 99.19 tokens/s, Accepted: 638 tokens, Drafted: 992 tokens, Per-position acceptance rate: 0.754, 0.532, Avg Draft acceptance rate: 64.3%
(APIServer pid=1) INFO: 172.21.0.1:52418 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:22:32 [loggers.py:323] Engine 000: Avg prompt throughput: 8.6 tokens/s, Avg generation throughput: 139.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 52.5%, MM cache hit rate: 77.8%
(APIServer pid=1) INFO 09-18 14:22:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.53, Accepted throughput: 84.50 tokens/s, Drafted throughput: 110.60 tokens/s, Accepted: 845 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.848, 0.680, Avg Draft acceptance rate: 76.4%
(APIServer pid=1) INFO 09-18 14:22:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 134.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 52.5%, MM cache hit rate: 77.8%
(APIServer pid=1) INFO 09-18 14:22:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.40, Accepted throughput: 78.30 tokens/s, Drafted throughput: 112.00 tokens/s, Accepted: 783 tokens, Drafted: 1120 tokens, Per-position acceptance rate: 0.811, 0.588, Avg Draft acceptance rate: 69.9%
(APIServer pid=1) INFO: 127.0.0.1:56790 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53910 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:22:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 33.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 58.5%, Prefix cache hit rate: 44.1%, MM cache hit rate: 77.8%
(APIServer pid=1) INFO 09-18 14:22:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.42, Accepted throughput: 19.70 tokens/s, Drafted throughput: 27.80 tokens/s, Accepted: 197 tokens, Drafted: 278 tokens, Per-position acceptance rate: 0.799, 0.619, Avg Draft acceptance rate: 70.9%
(APIServer pid=1) INFO: 172.21.0.1:47694 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:47700 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:23:02 [loggers.py:323] Engine 000: Avg prompt throughput: 12912.6 tokens/s, Avg generation throughput: 24.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 30.8%, Prefix cache hit rate: 43.3%, MM cache hit rate: 81.8%
(APIServer pid=1) INFO 09-18 14:23:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.74, Accepted throughput: 15.50 tokens/s, Drafted throughput: 17.80 tokens/s, Accepted: 155 tokens, Drafted: 178 tokens, Per-position acceptance rate: 0.921, 0.820, Avg Draft acceptance rate: 87.1%
(APIServer pid=1) INFO: 172.21.0.1:47708 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:23:12 [loggers.py:323] Engine 000: Avg prompt throughput: 1215.4 tokens/s, Avg generation throughput: 118.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 43.3%, MM cache hit rate: 81.8%
(APIServer pid=1) INFO 09-18 14:23:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.24, Accepted throughput: 65.70 tokens/s, Drafted throughput: 105.99 tokens/s, Accepted: 657 tokens, Drafted: 1060 tokens, Per-position acceptance rate: 0.743, 0.496, Avg Draft acceptance rate: 62.0%
(APIServer pid=1) INFO: 127.0.0.1:53052 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59822 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:23:22 [loggers.py:323] Engine 000: Avg prompt throughput: 8.4 tokens/s, Avg generation throughput: 120.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 43.3%, MM cache hit rate: 81.8%
(APIServer pid=1) INFO 09-18 14:23:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.18, Accepted throughput: 65.40 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 654 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.716, 0.469, Avg Draft acceptance rate: 59.2%
(APIServer pid=1) INFO 09-18 14:23:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 121.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 43.3%, MM cache hit rate: 81.8%
(APIServer pid=1) INFO 09-18 14:23:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.18, Accepted throughput: 66.00 tokens/s, Drafted throughput: 111.60 tokens/s, Accepted: 660 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.704, 0.478, Avg Draft acceptance rate: 59.1%
(APIServer pid=1) INFO: 172.21.0.1:34388 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:23:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 61.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 46.2%, Prefix cache hit rate: 37.4%, MM cache hit rate: 81.8%
(APIServer pid=1) INFO 09-18 14:23:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.06, Accepted throughput: 31.80 tokens/s, Drafted throughput: 59.99 tokens/s, Accepted: 318 tokens, Drafted: 600 tokens, Per-position acceptance rate: 0.673, 0.387, Avg Draft acceptance rate: 53.0%
(APIServer pid=1) INFO: 127.0.0.1:50974 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:23:52 [loggers.py:323] Engine 000: Avg prompt throughput: 12598.6 tokens/s, Avg generation throughput: 2.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 81.5%, Prefix cache hit rate: 37.4%, MM cache hit rate: 81.8%
(APIServer pid=1) INFO 09-18 14:23:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.80, Accepted throughput: 1.80 tokens/s, Drafted throughput: 2.00 tokens/s, Accepted: 18 tokens, Drafted: 20 tokens, Per-position acceptance rate: 0.900, 0.900, Avg Draft acceptance rate: 90.0%
(APIServer pid=1) INFO: 172.21.0.1:50664 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:38410 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:38412 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:24:02 [loggers.py:323] Engine 000: Avg prompt throughput: 1529.0 tokens/s, Avg generation throughput: 105.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 36.8%, MM cache hit rate: 84.6%
(APIServer pid=1) INFO 09-18 14:24:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.35, Accepted throughput: 60.20 tokens/s, Drafted throughput: 89.20 tokens/s, Accepted: 602 tokens, Drafted: 892 tokens, Per-position acceptance rate: 0.791, 0.558, Avg Draft acceptance rate: 67.5%
(APIServer pid=1) INFO 09-18 14:24:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 118.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 36.8%, MM cache hit rate: 84.6%
(APIServer pid=1) INFO 09-18 14:24:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.13, Accepted throughput: 62.90 tokens/s, Drafted throughput: 111.40 tokens/s, Accepted: 629 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.689, 0.440, Avg Draft acceptance rate: 56.5%
(APIServer pid=1) INFO: 172.21.0.1:38508 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:37090 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:24:22 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 123.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 36.8%, MM cache hit rate: 84.6%
(APIServer pid=1) INFO 09-18 14:24:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.23, Accepted throughput: 67.80 tokens/s, Drafted throughput: 110.60 tokens/s, Accepted: 678 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.732, 0.494, Avg Draft acceptance rate: 61.3%
(APIServer pid=1) INFO: 172.21.0.1:55060 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:24:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 100.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 36.9%, Prefix cache hit rate: 32.5%, MM cache hit rate: 84.6%
(APIServer pid=1) INFO 09-18 14:24:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.33, Accepted throughput: 57.60 tokens/s, Drafted throughput: 86.60 tokens/s, Accepted: 576 tokens, Drafted: 866 tokens, Per-position acceptance rate: 0.762, 0.568, Avg Draft acceptance rate: 66.5%
(APIServer pid=1) INFO 09-18 14:24:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 78.5%, Prefix cache hit rate: 32.5%, MM cache hit rate: 84.6%
(APIServer pid=1) INFO: 127.0.0.1:41864 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:44650 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:44654 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:44658 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:24:52 [loggers.py:323] Engine 000: Avg prompt throughput: 14128.6 tokens/s, Avg generation throughput: 77.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 32.0%, MM cache hit rate: 86.7%
(APIServer pid=1) INFO 09-18 14:24:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.37, Accepted throughput: 22.20 tokens/s, Drafted throughput: 32.40 tokens/s, Accepted: 444 tokens, Drafted: 648 tokens, Per-position acceptance rate: 0.765, 0.605, Avg Draft acceptance rate: 68.5%
(APIServer pid=1) INFO 09-18 14:25:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 130.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 32.0%, MM cache hit rate: 86.7%
(APIServer pid=1) INFO 09-18 14:25:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.33, Accepted throughput: 74.49 tokens/s, Drafted throughput: 111.79 tokens/s, Accepted: 745 tokens, Drafted: 1118 tokens, Per-position acceptance rate: 0.767, 0.565, Avg Draft acceptance rate: 66.6%
(APIServer pid=1) INFO: 172.21.0.1:52324 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:25:12 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 124.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 32.0%, MM cache hit rate: 86.7%
(APIServer pid=1) INFO 09-18 14:25:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.25, Accepted throughput: 69.30 tokens/s, Drafted throughput: 110.99 tokens/s, Accepted: 693 tokens, Drafted: 1110 tokens, Per-position acceptance rate: 0.737, 0.512, Avg Draft acceptance rate: 62.4%
(APIServer pid=1) INFO: 127.0.0.1:54114 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:47722 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:25:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 32.3%, Prefix cache hit rate: 28.7%, MM cache hit rate: 86.7%
(APIServer pid=1) INFO 09-18 14:25:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.32, Accepted throughput: 63.90 tokens/s, Drafted throughput: 96.79 tokens/s, Accepted: 639 tokens, Drafted: 968 tokens, Per-position acceptance rate: 0.756, 0.564, Avg Draft acceptance rate: 66.0%
(APIServer pid=1) INFO 09-18 14:25:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 75.4%, Prefix cache hit rate: 28.7%, MM cache hit rate: 86.7%
(APIServer pid=1) INFO: 172.21.0.1:56320 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56330 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56334 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:25:42 [loggers.py:323] Engine 000: Avg prompt throughput: 14128.9 tokens/s, Avg generation throughput: 67.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 28.3%, MM cache hit rate: 88.2%
(APIServer pid=1) INFO 09-18 14:25:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.45, Accepted throughput: 19.80 tokens/s, Drafted throughput: 27.30 tokens/s, Accepted: 396 tokens, Drafted: 546 tokens, Per-position acceptance rate: 0.806, 0.645, Avg Draft acceptance rate: 72.5%
(APIServer pid=1) INFO: 127.0.0.1:34304 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:25:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 126.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 28.3%, MM cache hit rate: 88.2%
(APIServer pid=1) INFO 09-18 14:25:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.27, Accepted throughput: 70.90 tokens/s, Drafted throughput: 111.80 tokens/s, Accepted: 709 tokens, Drafted: 1118 tokens, Per-position acceptance rate: 0.757, 0.512, Avg Draft acceptance rate: 63.4%
(APIServer pid=1) INFO: 172.21.0.1:33198 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:26:02 [loggers.py:323] Engine 000: Avg prompt throughput: 8.5 tokens/s, Avg generation throughput: 117.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 28.3%, MM cache hit rate: 88.2%
(APIServer pid=1) INFO 09-18 14:26:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.12, Accepted throughput: 62.09 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 621 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.681, 0.444, Avg Draft acceptance rate: 56.2%
(APIServer pid=1) INFO 09-18 14:26:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 130.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 28.3%, MM cache hit rate: 88.2%
(APIServer pid=1) INFO 09-18 14:26:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.34, Accepted throughput: 74.39 tokens/s, Drafted throughput: 111.39 tokens/s, Accepted: 744 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.772, 0.564, Avg Draft acceptance rate: 66.8%
(APIServer pid=1) INFO: 172.21.0.1:52376 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:51278 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:26:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 69.2%, Prefix cache hit rate: 25.7%, MM cache hit rate: 88.2%
(APIServer pid=1) INFO 09-18 14:26:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 1.80, Accepted throughput: 0.40 tokens/s, Drafted throughput: 1.00 tokens/s, Accepted: 4 tokens, Drafted: 10 tokens, Per-position acceptance rate: 0.600, 0.200, Avg Draft acceptance rate: 40.0%
(APIServer pid=1) INFO: 172.21.0.1:56900 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56902 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56906 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:26:32 [loggers.py:323] Engine 000: Avg prompt throughput: 14128.0 tokens/s, Avg generation throughput: 53.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 25.4%, MM cache hit rate: 89.5%
(APIServer pid=1) INFO 09-18 14:26:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.74, Accepted throughput: 33.90 tokens/s, Drafted throughput: 39.00 tokens/s, Accepted: 339 tokens, Drafted: 390 tokens, Per-position acceptance rate: 0.923, 0.815, Avg Draft acceptance rate: 86.9%
(APIServer pid=1) INFO 09-18 14:26:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 112.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 25.4%, MM cache hit rate: 89.5%
(APIServer pid=1) INFO 09-18 14:26:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.01, Accepted throughput: 56.60 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 566 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.658, 0.357, Avg Draft acceptance rate: 50.7%
(APIServer pid=1) INFO: 127.0.0.1:50340 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:37702 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:26:52 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 117.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 25.4%, MM cache hit rate: 89.5%
(APIServer pid=1) INFO 09-18 14:26:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.12, Accepted throughput: 62.10 tokens/s, Drafted throughput: 110.80 tokens/s, Accepted: 621 tokens, Drafted: 1108 tokens, Per-position acceptance rate: 0.704, 0.417, Avg Draft acceptance rate: 56.0%
(APIServer pid=1) INFO 09-18 14:27:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 25.4%, MM cache hit rate: 89.5%
(APIServer pid=1) INFO 09-18 14:27:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.17, Accepted throughput: 65.20 tokens/s, Drafted throughput: 111.40 tokens/s, Accepted: 652 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.707, 0.463, Avg Draft acceptance rate: 58.5%
(APIServer pid=1) INFO: 172.21.0.1:41528 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:27:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 45.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 53.8%, Prefix cache hit rate: 23.2%, MM cache hit rate: 89.5%
(APIServer pid=1) INFO 09-18 14:27:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.25, Accepted throughput: 25.40 tokens/s, Drafted throughput: 40.80 tokens/s, Accepted: 254 tokens, Drafted: 408 tokens, Per-position acceptance rate: 0.745, 0.500, Avg Draft acceptance rate: 62.3%
(APIServer pid=1) INFO: 127.0.0.1:34370 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:60904 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:27:22 [loggers.py:323] Engine 000: Avg prompt throughput: 12913.2 tokens/s, Avg generation throughput: 22.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 23.1%, Prefix cache hit rate: 23.2%, MM cache hit rate: 90.0%
(APIServer pid=1) INFO 09-18 14:27:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.66, Accepted throughput: 14.10 tokens/s, Drafted throughput: 17.00 tokens/s, Accepted: 141 tokens, Drafted: 170 tokens, Per-position acceptance rate: 0.894, 0.765, Avg Draft acceptance rate: 82.9%
(APIServer pid=1) INFO: 172.21.0.1:60920 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:33700 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:27:32 [loggers.py:323] Engine 000: Avg prompt throughput: 1215.4 tokens/s, Avg generation throughput: 98.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 23.0%, MM cache hit rate: 90.5%
(APIServer pid=1) INFO 09-18 14:27:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.09, Accepted throughput: 51.20 tokens/s, Drafted throughput: 93.60 tokens/s, Accepted: 512 tokens, Drafted: 936 tokens, Per-position acceptance rate: 0.660, 0.434, Avg Draft acceptance rate: 54.7%
(APIServer pid=1) INFO: 172.21.0.1:44936 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:27:42 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 134.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 23.0%, MM cache hit rate: 90.5%
(APIServer pid=1) INFO 09-18 14:27:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.43, Accepted throughput: 79.30 tokens/s, Drafted throughput: 110.60 tokens/s, Accepted: 793 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.817, 0.617, Avg Draft acceptance rate: 71.7%
(APIServer pid=1) INFO: 127.0.0.1:45276 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:27:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 118.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 23.0%, MM cache hit rate: 90.5%
(APIServer pid=1) INFO 09-18 14:27:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.11, Accepted throughput: 62.10 tokens/s, Drafted throughput: 111.80 tokens/s, Accepted: 621 tokens, Drafted: 1118 tokens, Per-position acceptance rate: 0.699, 0.411, Avg Draft acceptance rate: 55.5%
(APIServer pid=1) INFO: 172.21.0.1:34630 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:28:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 76.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 43.1%, Prefix cache hit rate: 21.2%, MM cache hit rate: 90.5%
(APIServer pid=1) INFO 09-18 14:28:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 41.10 tokens/s, Drafted throughput: 70.60 tokens/s, Accepted: 411 tokens, Drafted: 706 tokens, Per-position acceptance rate: 0.711, 0.453, Avg Draft acceptance rate: 58.2%
(APIServer pid=1) INFO 09-18 14:28:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 84.6%, Prefix cache hit rate: 21.2%, MM cache hit rate: 90.5%
(APIServer pid=1) INFO: 172.21.0.1:47082 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:37824 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:49298 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:37832 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:28:22 [loggers.py:323] Engine 000: Avg prompt throughput: 14128.0 tokens/s, Avg generation throughput: 98.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 21.0%, MM cache hit rate: 91.3%
(APIServer pid=1) INFO 09-18 14:28:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.41, Accepted throughput: 28.70 tokens/s, Drafted throughput: 40.60 tokens/s, Accepted: 574 tokens, Drafted: 812 tokens, Per-position acceptance rate: 0.793, 0.621, Avg Draft acceptance rate: 70.7%
(APIServer pid=1) INFO 09-18 14:28:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 124.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 21.0%, MM cache hit rate: 91.3%
(APIServer pid=1) INFO 09-18 14:28:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.24, Accepted throughput: 69.10 tokens/s, Drafted throughput: 111.20 tokens/s, Accepted: 691 tokens, Drafted: 1112 tokens, Per-position acceptance rate: 0.745, 0.498, Avg Draft acceptance rate: 62.1%
(APIServer pid=1) INFO: 172.21.0.1:53742 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:28:42 [loggers.py:323] Engine 000: Avg prompt throughput: 8.5 tokens/s, Avg generation throughput: 111.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 21.0%, MM cache hit rate: 91.3%
(APIServer pid=1) INFO 09-18 14:28:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.02, Accepted throughput: 56.50 tokens/s, Drafted throughput: 110.40 tokens/s, Accepted: 565 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.650, 0.373, Avg Draft acceptance rate: 51.2%
(APIServer pid=1) INFO: 127.0.0.1:49254 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:44080 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:28:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 111.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 33.8%, Prefix cache hit rate: 19.5%, MM cache hit rate: 91.3%
(APIServer pid=1) INFO 09-18 14:28:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.40, Accepted throughput: 64.89 tokens/s, Drafted throughput: 92.59 tokens/s, Accepted: 649 tokens, Drafted: 926 tokens, Per-position acceptance rate: 0.803, 0.598, Avg Draft acceptance rate: 70.1%
(APIServer pid=1) INFO 09-18 14:29:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 76.9%, Prefix cache hit rate: 19.5%, MM cache hit rate: 91.3%
(APIServer pid=1) INFO: 172.21.0.1:53800 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53804 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53806 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:29:12 [loggers.py:323] Engine 000: Avg prompt throughput: 14128.1 tokens/s, Avg generation throughput: 75.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 19.4%, MM cache hit rate: 92.0%
(APIServer pid=1) INFO 09-18 14:29:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.57, Accepted throughput: 23.05 tokens/s, Drafted throughput: 29.40 tokens/s, Accepted: 461 tokens, Drafted: 588 tokens, Per-position acceptance rate: 0.864, 0.704, Avg Draft acceptance rate: 78.4%
(APIServer pid=1) INFO: 127.0.0.1:51408 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:29:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 118.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 19.4%, MM cache hit rate: 92.0%
(APIServer pid=1) INFO 09-18 14:29:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.13, Accepted throughput: 62.89 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 629 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.703, 0.425, Avg Draft acceptance rate: 56.4%
(APIServer pid=1) INFO: 172.21.0.1:60596 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:29:32 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 124.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 19.4%, MM cache hit rate: 92.0%
(APIServer pid=1) INFO 09-18 14:29:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.25, Accepted throughput: 68.89 tokens/s, Drafted throughput: 110.59 tokens/s, Accepted: 689 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.732, 0.514, Avg Draft acceptance rate: 62.3%
(APIServer pid=1) INFO 09-18 14:29:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 119.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 19.4%, MM cache hit rate: 92.0%
(APIServer pid=1) INFO 09-18 14:29:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.15, Accepted throughput: 64.20 tokens/s, Drafted throughput: 111.20 tokens/s, Accepted: 642 tokens, Drafted: 1112 tokens, Per-position acceptance rate: 0.716, 0.439, Avg Draft acceptance rate: 57.7%
(APIServer pid=1) INFO: 172.21.0.1:60372 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:41996 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:29:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 66.2%, Prefix cache hit rate: 18.1%, MM cache hit rate: 92.0%
(APIServer pid=1) INFO 09-18 14:29:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.23, Accepted throughput: 6.40 tokens/s, Drafted throughput: 10.40 tokens/s, Accepted: 64 tokens, Drafted: 104 tokens, Per-position acceptance rate: 0.769, 0.462, Avg Draft acceptance rate: 61.5%
(APIServer pid=1) INFO: 172.21.0.1:59394 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59402 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59410 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:30:02 [loggers.py:323] Engine 000: Avg prompt throughput: 14127.4 tokens/s, Avg generation throughput: 41.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 18.0%, MM cache hit rate: 92.6%
(APIServer pid=1) INFO 09-18 14:30:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.76, Accepted throughput: 26.00 tokens/s, Drafted throughput: 29.60 tokens/s, Accepted: 260 tokens, Drafted: 296 tokens, Per-position acceptance rate: 0.912, 0.845, Avg Draft acceptance rate: 87.8%
(APIServer pid=1) INFO 09-18 14:30:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 117.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 18.0%, MM cache hit rate: 92.6%
(APIServer pid=1) INFO 09-18 14:30:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.10, Accepted throughput: 61.50 tokens/s, Drafted throughput: 111.39 tokens/s, Accepted: 615 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.666, 0.438, Avg Draft acceptance rate: 55.2%
(APIServer pid=1) INFO: 127.0.0.1:43480 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:48952 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:30:22 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 119.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 18.0%, MM cache hit rate: 92.6%
(APIServer pid=1) INFO 09-18 14:30:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 63.90 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 639 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.699, 0.458, Avg Draft acceptance rate: 57.9%
(APIServer pid=1) INFO 09-18 14:30:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 18.0%, MM cache hit rate: 92.6%
(APIServer pid=1) INFO 09-18 14:30:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 65.00 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 650 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.706, 0.459, Avg Draft acceptance rate: 58.2%
(APIServer pid=1) INFO: 172.21.0.1:50314 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:30:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 52.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 50.8%, Prefix cache hit rate: 16.9%, MM cache hit rate: 92.6%
(APIServer pid=1) INFO 09-18 14:30:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 28.10 tokens/s, Drafted throughput: 48.40 tokens/s, Accepted: 281 tokens, Drafted: 484 tokens, Per-position acceptance rate: 0.665, 0.496, Avg Draft acceptance rate: 58.1%
(APIServer pid=1) INFO: 127.0.0.1:50034 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:58630 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:30:52 [loggers.py:323] Engine 000: Avg prompt throughput: 12598.1 tokens/s, Avg generation throughput: 13.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 16.8%, MM cache hit rate: 92.9%
(APIServer pid=1) INFO 09-18 14:30:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.71, Accepted throughput: 8.40 tokens/s, Drafted throughput: 9.80 tokens/s, Accepted: 84 tokens, Drafted: 98 tokens, Per-position acceptance rate: 0.878, 0.837, Avg Draft acceptance rate: 85.7%
(APIServer pid=1) INFO: 172.21.0.1:58644 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:38342 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:31:02 [loggers.py:323] Engine 000: Avg prompt throughput: 1529.0 tokens/s, Avg generation throughput: 110.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 16.7%, MM cache hit rate: 93.1%
(APIServer pid=1) INFO 09-18 14:31:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.35, Accepted throughput: 63.19 tokens/s, Drafted throughput: 93.59 tokens/s, Accepted: 632 tokens, Drafted: 936 tokens, Per-position acceptance rate: 0.778, 0.573, Avg Draft acceptance rate: 67.5%
(APIServer pid=1) INFO: 172.21.0.1:49568 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:31:12 [loggers.py:323] Engine 000: Avg prompt throughput: 8.5 tokens/s, Avg generation throughput: 126.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 16.7%, MM cache hit rate: 93.1%
(APIServer pid=1) INFO 09-18 14:31:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.30, Accepted throughput: 71.59 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 716 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.766, 0.531, Avg Draft acceptance rate: 64.9%
(APIServer pid=1) INFO: 127.0.0.1:53428 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:31:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 16.7%, MM cache hit rate: 93.1%
(APIServer pid=1) INFO 09-18 14:31:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.16, Accepted throughput: 65.00 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 650 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.703, 0.462, Avg Draft acceptance rate: 58.2%
(APIServer pid=1) INFO: 172.21.0.1:53214 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:31:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 78.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 40.0%, Prefix cache hit rate: 15.8%, MM cache hit rate: 93.1%
(APIServer pid=1) INFO 09-18 14:31:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.02, Accepted throughput: 39.70 tokens/s, Drafted throughput: 77.60 tokens/s, Accepted: 397 tokens, Drafted: 776 tokens, Per-position acceptance rate: 0.631, 0.392, Avg Draft acceptance rate: 51.2%
(APIServer pid=1) INFO 09-18 14:31:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 81.5%, Prefix cache hit rate: 15.8%, MM cache hit rate: 93.1%
(APIServer pid=1) INFO: 172.21.0.1:59288 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:56286 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59294 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59298 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:31:52 [loggers.py:323] Engine 000: Avg prompt throughput: 14129.1 tokens/s, Avg generation throughput: 88.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:31:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.40, Accepted throughput: 25.75 tokens/s, Drafted throughput: 36.80 tokens/s, Accepted: 515 tokens, Drafted: 736 tokens, Per-position acceptance rate: 0.788, 0.611, Avg Draft acceptance rate: 70.0%
(APIServer pid=1) INFO 09-18 14:32:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:32:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.15, Accepted throughput: 64.30 tokens/s, Drafted throughput: 111.40 tokens/s, Accepted: 643 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.713, 0.442, Avg Draft acceptance rate: 57.7%
(APIServer pid=1) INFO: 172.21.0.1:40376 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:32:12 [loggers.py:323] Engine 000: Avg prompt throughput: 8.7 tokens/s, Avg generation throughput: 129.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:32:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.35, Accepted throughput: 74.70 tokens/s, Drafted throughput: 110.40 tokens/s, Accepted: 747 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.775, 0.578, Avg Draft acceptance rate: 67.7%
(APIServer pid=1) INFO: 127.0.0.1:51024 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:54062 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:32:22 [loggers.py:323] Engine 000: Avg prompt throughput: 25.2 tokens/s, Avg generation throughput: 127.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:32:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.35, Accepted throughput: 73.19 tokens/s, Drafted throughput: 108.79 tokens/s, Accepted: 732 tokens, Drafted: 1088 tokens, Per-position acceptance rate: 0.774, 0.572, Avg Draft acceptance rate: 67.3%
(APIServer pid=1) INFO: 172.21.0.1:54076 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:54078 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53562 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:32:32 [loggers.py:323] Engine 000: Avg prompt throughput: 38.1 tokens/s, Avg generation throughput: 133.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:32:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.48, Accepted throughput: 79.80 tokens/s, Drafted throughput: 107.80 tokens/s, Accepted: 798 tokens, Drafted: 1078 tokens, Per-position acceptance rate: 0.831, 0.649, Avg Draft acceptance rate: 74.0%
(APIServer pid=1) INFO 09-18 14:32:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 128.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:32:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.32, Accepted throughput: 73.10 tokens/s, Drafted throughput: 110.60 tokens/s, Accepted: 731 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.750, 0.571, Avg Draft acceptance rate: 66.1%
(APIServer pid=1) INFO: 127.0.0.1:36210 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53576 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:32:52 [loggers.py:323] Engine 000: Avg prompt throughput: 13.4 tokens/s, Avg generation throughput: 131.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:32:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.42, Accepted throughput: 77.20 tokens/s, Drafted throughput: 109.00 tokens/s, Accepted: 772 tokens, Drafted: 1090 tokens, Per-position acceptance rate: 0.796, 0.620, Avg Draft acceptance rate: 70.8%
(APIServer pid=1) INFO: 172.21.0.1:38118 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:47594 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:47610 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:47622 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:33:02 [loggers.py:323] Engine 000: Avg prompt throughput: 59.9 tokens/s, Avg generation throughput: 137.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:33:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.59, Accepted throughput: 84.40 tokens/s, Drafted throughput: 106.20 tokens/s, Accepted: 844 tokens, Drafted: 1062 tokens, Per-position acceptance rate: 0.868, 0.721, Avg Draft acceptance rate: 79.5%
(APIServer pid=1) INFO: 172.21.0.1:47632 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:47648 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:45364 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:33:12 [loggers.py:323] Engine 000: Avg prompt throughput: 27.9 tokens/s, Avg generation throughput: 142.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:33:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.64, Accepted throughput: 88.50 tokens/s, Drafted throughput: 108.00 tokens/s, Accepted: 885 tokens, Drafted: 1080 tokens, Per-position acceptance rate: 0.891, 0.748, Avg Draft acceptance rate: 81.9%
(APIServer pid=1) INFO: 172.21.0.1:45372 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:45386 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:47374 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:33:22 [loggers.py:323] Engine 000: Avg prompt throughput: 32.5 tokens/s, Avg generation throughput: 28.2 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 15.6%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO 09-18 14:33:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.86, Accepted throughput: 18.40 tokens/s, Drafted throughput: 19.80 tokens/s, Accepted: 184 tokens, Drafted: 198 tokens, Per-position acceptance rate: 0.970, 0.889, Avg Draft acceptance rate: 92.9%
(APIServer pid=1) INFO 09-18 14:33:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 15.6%, MM cache hit rate: 93.5%
(APIServer pid=1) INFO: 127.0.0.1:51446 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:47488 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:50100 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:54884 - "GET /metrics HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:49228 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:45014 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:45300 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:46998 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:51132 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.16.100.3:62103 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.16.100.3:62104 - "GET /v1/models HTTP/1.1" 401 Unauthorized
(APIServer pid=1) INFO: 127.0.0.1:58480 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:46524 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:53330 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:55746 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:56396 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:55482 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:56702 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:36636 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:34060 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:44360 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:52262 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:60346 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:32864 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:47770 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:59988 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:47698 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:44138 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:52264 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:52764 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:54950 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:37836 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:50426 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:42744 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:36986 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:46082 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:33154 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:33156 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35076 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35092 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35102 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35110 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35124 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35134 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35136 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35150 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35160 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35174 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35188 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35192 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35200 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:35204 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:50:02 [loggers.py:323] Engine 000: Avg prompt throughput: 399.3 tokens/s, Avg generation throughput: 105.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 23.1%, Prefix cache hit rate: 15.6%, MM cache hit rate: 93.8%
(APIServer pid=1) INFO 09-18 14:50:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.84, Accepted throughput: 0.68 tokens/s, Drafted throughput: 0.74 tokens/s, Accepted: 679 tokens, Drafted: 740 tokens, Per-position acceptance rate: 0.957, 0.878, Avg Draft acceptance rate: 91.8%
(APIServer pid=1) INFO: 172.21.0.1:35214 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56506 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56510 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:56514 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:50:12 [loggers.py:323] Engine 000: Avg prompt throughput: 1821.0 tokens/s, Avg generation throughput: 96.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:50:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.32, Accepted throughput: 55.10 tokens/s, Drafted throughput: 83.40 tokens/s, Accepted: 551 tokens, Drafted: 834 tokens, Per-position acceptance rate: 0.763, 0.559, Avg Draft acceptance rate: 66.1%
(APIServer pid=1) INFO: 127.0.0.1:55476 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:50:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 127.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:50:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.29, Accepted throughput: 72.00 tokens/s, Drafted throughput: 111.60 tokens/s, Accepted: 720 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.758, 0.532, Avg Draft acceptance rate: 64.5%
(APIServer pid=1) INFO: 172.21.0.1:37334 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:50:32 [loggers.py:323] Engine 000: Avg prompt throughput: 7.7 tokens/s, Avg generation throughput: 122.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:50:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.21, Accepted throughput: 66.99 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 670 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.725, 0.489, Avg Draft acceptance rate: 60.7%
(APIServer pid=1) INFO: 172.21.0.1:37138 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:50:42 [loggers.py:323] Engine 000: Avg prompt throughput: 7.7 tokens/s, Avg generation throughput: 121.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:50:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.20, Accepted throughput: 66.00 tokens/s, Drafted throughput: 110.39 tokens/s, Accepted: 660 tokens, Drafted: 1104 tokens, Per-position acceptance rate: 0.728, 0.467, Avg Draft acceptance rate: 59.8%
(APIServer pid=1) INFO: 127.0.0.1:53092 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:50:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 126.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:50:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.27, Accepted throughput: 70.60 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 706 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.742, 0.523, Avg Draft acceptance rate: 63.3%
(APIServer pid=1) INFO: 172.21.0.1:39218 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:39220 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:51:02 [loggers.py:323] Engine 000: Avg prompt throughput: 15.8 tokens/s, Avg generation throughput: 121.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:51:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.22, Accepted throughput: 66.50 tokens/s, Drafted throughput: 109.40 tokens/s, Accepted: 665 tokens, Drafted: 1094 tokens, Per-position acceptance rate: 0.729, 0.486, Avg Draft acceptance rate: 60.8%
(APIServer pid=1) INFO 09-18 14:51:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 127.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:51:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.27, Accepted throughput: 71.20 tokens/s, Drafted throughput: 112.00 tokens/s, Accepted: 712 tokens, Drafted: 1120 tokens, Per-position acceptance rate: 0.750, 0.521, Avg Draft acceptance rate: 63.6%
(APIServer pid=1) INFO: 172.21.0.1:41374 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:37916 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:51:22 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 128.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:51:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.32, Accepted throughput: 73.29 tokens/s, Drafted throughput: 110.79 tokens/s, Accepted: 733 tokens, Drafted: 1108 tokens, Per-position acceptance rate: 0.769, 0.554, Avg Draft acceptance rate: 66.2%
(APIServer pid=1) INFO 09-18 14:51:32 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 128.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:51:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.30, Accepted throughput: 72.70 tokens/s, Drafted throughput: 111.60 tokens/s, Accepted: 727 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.758, 0.545, Avg Draft acceptance rate: 65.1%
(APIServer pid=1) INFO: 172.21.0.1:49184 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:51:42 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 127.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:51:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.30, Accepted throughput: 72.30 tokens/s, Drafted throughput: 111.00 tokens/s, Accepted: 723 tokens, Drafted: 1110 tokens, Per-position acceptance rate: 0.769, 0.533, Avg Draft acceptance rate: 65.1%
(APIServer pid=1) INFO: 172.21.0.1:39208 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:55292 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:39224 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:51:52 [loggers.py:323] Engine 000: Avg prompt throughput: 15.8 tokens/s, Avg generation throughput: 125.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:51:52 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.29, Accepted throughput: 71.00 tokens/s, Drafted throughput: 109.99 tokens/s, Accepted: 710 tokens, Drafted: 1100 tokens, Per-position acceptance rate: 0.744, 0.547, Avg Draft acceptance rate: 64.5%
(APIServer pid=1) INFO 09-18 14:52:02 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 120.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:52:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.15, Accepted throughput: 64.39 tokens/s, Drafted throughput: 111.59 tokens/s, Accepted: 644 tokens, Drafted: 1116 tokens, Per-position acceptance rate: 0.697, 0.457, Avg Draft acceptance rate: 57.7%
(APIServer pid=1) INFO: 172.21.0.1:53966 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:52:12 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 123.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:52:12 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.23, Accepted throughput: 67.80 tokens/s, Drafted throughput: 110.59 tokens/s, Accepted: 678 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.722, 0.505, Avg Draft acceptance rate: 61.3%
(APIServer pid=1) INFO: 127.0.0.1:53434 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:52:22 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 121.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:52:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.18, Accepted throughput: 66.00 tokens/s, Drafted throughput: 111.39 tokens/s, Accepted: 660 tokens, Drafted: 1114 tokens, Per-position acceptance rate: 0.715, 0.470, Avg Draft acceptance rate: 59.2%
(APIServer pid=1) INFO: 172.21.0.1:58938 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:52:32 [loggers.py:323] Engine 000: Avg prompt throughput: 7.9 tokens/s, Avg generation throughput: 121.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:52:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.19, Accepted throughput: 65.60 tokens/s, Drafted throughput: 110.60 tokens/s, Accepted: 656 tokens, Drafted: 1106 tokens, Per-position acceptance rate: 0.712, 0.474, Avg Draft acceptance rate: 59.3%
(APIServer pid=1) INFO: 172.21.0.1:59878 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59890 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59894 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59900 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59908 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59912 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59914 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59930 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59932 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59944 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59950 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:52:42 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 105.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 15.7%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO 09-18 14:52:42 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.20, Accepted throughput: 57.80 tokens/s, Drafted throughput: 96.20 tokens/s, Accepted: 578 tokens, Drafted: 962 tokens, Per-position acceptance rate: 0.711, 0.491, Avg Draft acceptance rate: 60.1%
(APIServer pid=1) INFO: 172.21.0.1:59952 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59958 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59968 - "POST /tokenize HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:59980 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:55976 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:52:52 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 69.2%, Prefix cache hit rate: 14.9%, MM cache hit rate: 94.6%
(APIServer pid=1) INFO: 172.21.0.1:32818 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:32834 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:32836 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:53:02 [loggers.py:323] Engine 000: Avg prompt throughput: 13599.1 tokens/s, Avg generation throughput: 35.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 33.8%, Prefix cache hit rate: 21.8%, MM cache hit rate: 94.7%
(APIServer pid=1) INFO 09-18 14:53:02 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.79, Accepted throughput: 11.35 tokens/s, Drafted throughput: 12.70 tokens/s, Accepted: 227 tokens, Drafted: 254 tokens, Per-position acceptance rate: 0.913, 0.874, Avg Draft acceptance rate: 89.4%
(APIServer pid=1) INFO 09-18 14:53:12 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 76.9%, Prefix cache hit rate: 21.8%, MM cache hit rate: 94.7%
(APIServer pid=1) INFO: 172.21.0.1:53668 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53676 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53688 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53696 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53700 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 127.0.0.1:44356 - "GET /health HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53716 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53720 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:53:22 [loggers.py:323] Engine 000: Avg prompt throughput: 11222.0 tokens/s, Avg generation throughput: 125.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 21.8%, MM cache hit rate: 94.7%
(APIServer pid=1) INFO 09-18 14:53:22 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.77, Accepted throughput: 40.25 tokens/s, Drafted throughput: 45.40 tokens/s, Accepted: 805 tokens, Drafted: 908 tokens, Per-position acceptance rate: 0.943, 0.830, Avg Draft acceptance rate: 88.7%
(APIServer pid=1) INFO: 172.21.0.1:53732 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:53748 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO 09-18 14:53:32 [loggers.py:323] Engine 000: Avg prompt throughput: 17.3 tokens/s, Avg generation throughput: 144.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 21.8%, MM cache hit rate: 94.7%
(APIServer pid=1) INFO 09-18 14:53:32 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.66, Accepted throughput: 90.39 tokens/s, Drafted throughput: 108.99 tokens/s, Accepted: 904 tokens, Drafted: 1090 tokens, Per-position acceptance rate: 0.899, 0.760, Avg Draft acceptance rate: 82.9%
(APIServer pid=1) INFO: 172.21.0.1:40154 - "POST /v1/chat/completions HTTP/1.1" 200 OK
(APIServer pid=1) INFO: 172.21.0.1:40170 - "POST /v1/chat/completions HTTP/1.1" 200 OK
audit/tuning/steps-123/mtp2-b2048/status.json
+5
View File
@@ -0,0 +1,5 @@
{
"startup": true,
"records": 44,
"failures": []
}