Document MTP 2 speed and memory tradeoff; retain stable default
This commit is contained in:
@@ -0,0 +1,230 @@
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [api_utils.py:347]
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [api_utils.py:347] █ █ █▄ ▄█
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [api_utils.py:347] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.3.1.dev3+g0bfc7a15d
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [api_utils.py:347] █▄█▀ █ █ █ █ model /model
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [api_utils.py:347] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [api_utils.py:347]
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [model.py:691] Resolved architecture: Qwen4ExpForConditionalGeneration
|
||||
(APIServer pid=1) INFO 09-18 02:55:12 [model.py:2024] Using max model len 131072
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) INFO 09-18 02:55:15 [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) INFO 09-18 02:55:15 [model.py:691] Resolved architecture: Qwen4ExpMTP
|
||||
(APIServer pid=1) INFO 09-18 02:55:15 [model.py:2024] Using max model len 262144
|
||||
(APIServer pid=1) WARNING 09-18 02:55:15 [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 02:55:15 [speculative.py:1653] Overriding draft model max model len from 262144 to 131072
|
||||
(APIServer pid=1) INFO 09-18 02:55:15 [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 02:55:15 [vllm.py:1271] Resolved Engram configuration: EngramConfig(cpu_offload=True, embedding_across_dp=False, dp_shared_memory=False)
|
||||
(APIServer pid=1) INFO 09-18 02:55:15 [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 02:55:15 [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 02:55:15 [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 02:55:15 [compilation.py:331] Enabled custom fusions: norm_quant, act_quant
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) INFO 09-18 02:55:28 [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)
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) INFO 09-18 02:55:29 [parallel_state.py:1825] world_size=1 rank=0 local_rank=0 distributed_init_method=file:///tmp/vllm_dist_12361652d17045ad82ebf3d8d70939b6 backend=nccl
|
||||
(EngineCore pid=112) INFO 09-18 02:55:29 [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=112) INFO 09-18 02:55:29 [gpu_worker.py:441] Using V2 Model Runner
|
||||
(EngineCore pid=112) INFO 09-18 02:55:30 [model_runner.py:387] Loading model from scratch...
|
||||
(EngineCore pid=112) INFO 09-18 02:55:30 [cuda.py:595] Using backend AttentionBackendEnum.FLASH_ATTN for vit attention
|
||||
(EngineCore pid=112) INFO 09-18 02:55:30 [mm_encoder_attention.py:372] Using AttentionBackendEnum.FLASH_ATTN for MMEncoderAttention.
|
||||
(EngineCore pid=112) INFO 09-18 02:55:30 [qwen_gdn_linear_attn.py:176] Using FlashInfer GDN prefill kernel (requested=auto, head_k_dim=128).
|
||||
(EngineCore pid=112) INFO 09-18 02:55:30 [qwen_gdn_linear_attn.py:528] GDN decode kernel: cuda
|
||||
(EngineCore pid=112) INFO 09-18 02:55:32 [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 02:55:34 [base.py:261] Multi-modal warmup completed in 12.188s
|
||||
(APIServer pid=1) INFO 09-18 02:55:35 [base.py:261] Readonly multi-modal warmup completed in 1.309s
|
||||
(EngineCore pid=112) INFO 09-18 02:56:05 [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=112) INFO 09-18 02:56:05 [flash_attn.py:1115] Using FlashAttention version 2
|
||||
(EngineCore pid=112) WARNING 09-18 02:56:06 [compilation.py:1350] Op 'quant_fp8' not present in model, enabling with '+quant_fp8' has no effect
|
||||
(EngineCore pid=112) INFO 09-18 02:56:06 [weight_utils.py:900] Filesystem type for checkpoints: EXT4. Checkpoint size: 123.57 GiB. Available RAM: 142.29 GiB.
|
||||
(EngineCore pid=112) INFO 09-18 02:56:06 [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=112) ␍Loading safetensors checkpoint shards: 0% Completed | 0/11 [00:00<?, ?it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 9% Completed | 1/11 [00:01<00:16, 1.63s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 18% Completed | 2/11 [00:06<00:33, 3.78s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 27% Completed | 3/11 [00:12<00:36, 4.57s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 36% Completed | 4/11 [00:17<00:34, 4.95s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 45% Completed | 5/11 [00:23<00:31, 5.20s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 55% Completed | 6/11 [00:29<00:26, 5.36s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 64% Completed | 7/11 [00:34<00:21, 5.45s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 73% Completed | 8/11 [00:40<00:16, 5.53s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 82% Completed | 9/11 [00:42<00:08, 4.25s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:42<00:00, 2.43s/it]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:42<00:00, 3.89s/it]
|
||||
(EngineCore pid=112)
|
||||
(EngineCore pid=112) INFO 09-18 02:56:49 [default_loader.py:430] Loading weights took 42.97 seconds
|
||||
(EngineCore pid=112) INFO 09-18 02:56:49 [nvfp4.py:611] Using MoEPrepareAndFinalizeNoDPEPModular
|
||||
(EngineCore pid=112) INFO 09-18 02:56:49 [vllm.py:1271] Resolved Engram configuration: EngramConfig(cpu_offload=True, embedding_across_dp=False, dp_shared_memory=False)
|
||||
(EngineCore pid=112) INFO 09-18 02:56:49 [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=112) WARNING 09-18 02:56:49 [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=112) INFO 09-18 02:56:49 [compilation.py:331] Enabled custom fusions: norm_quant, act_quant
|
||||
(EngineCore pid=112) INFO 09-18 02:56:50 [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=112) INFO 09-18 02:56:50 [weight_utils.py:900] Filesystem type for checkpoints: EXT4. Checkpoint size: 123.57 GiB. Available RAM: 142.10 GiB.
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 0% Completed | 0/11 [00:00<?, ?it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 18% Completed | 2/11 [00:00<00:01, 5.24it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 27% Completed | 3/11 [00:00<00:01, 4.08it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 36% Completed | 4/11 [00:01<00:01, 3.67it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 45% Completed | 5/11 [00:01<00:01, 3.45it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 55% Completed | 6/11 [00:01<00:01, 3.32it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 64% Completed | 7/11 [00:01<00:01, 3.26it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 73% Completed | 8/11 [00:02<00:00, 3.21it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 82% Completed | 9/11 [00:02<00:00, 3.71it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:02<00:00, 3.89it/s]
|
||||
(EngineCore pid=112) ␍Loading safetensors checkpoint shards: 100% Completed | 11/11 [00:02<00:00, 3.70it/s]
|
||||
(EngineCore pid=112)
|
||||
(EngineCore pid=112) INFO 09-18 02:56:53 [default_loader.py:430] Loading weights took 2.98 seconds
|
||||
(EngineCore pid=112) INFO 09-18 02:56:53 [deep_gemm.py:196] deep_gemm not found in site-packages, trying vendored vllm.third_party.deep_gemm
|
||||
(EngineCore pid=112) INFO 09-18 02:56:53 [deep_gemm.py:223] DeepGEMM PDL enabled on vllm.third_party.deep_gemm.
|
||||
(EngineCore pid=112) INFO 09-18 02:56:53 [deep_gemm.py:136] DeepGEMM E8M0 enabled on current platform.
|
||||
(EngineCore pid=112) INFO 09-18 02:56:56 [fp8.py:733] Using MoEPrepareAndFinalizeNoDPEPModular
|
||||
(EngineCore pid=112) WARNING 09-18 02:56:56 [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=112) INFO 09-18 02:56:57 [model_runner.py:419] Model loading took 76.36 GiB memory and 86.921433 seconds
|
||||
(EngineCore pid=112) INFO 09-18 02:56:57 [topk_topp_sampler.py:78] Using FlashInfer for top-p & top-k sampling.
|
||||
(EngineCore pid=112) INFO 09-18 02:56:57 [interface.py:918] Setting attention block size to 3184 tokens to ensure that attention page size is >= mamba page size.
|
||||
(EngineCore pid=112) INFO 09-18 02:56:57 [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=112) INFO 09-18 02:56:57 [utils.py:320] Using BLNHC KV cache layout.
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [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=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) [transformers] Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
||||
(EngineCore pid=112) INFO 09-18 02:57:01 [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=112) WARNING 09-18 02:57:23 [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=112) WARNING 09-18 02:57:23 [compilation.py:1415] CUDAGraphMode.FULL is not supported with GDNAttentionBackend backend (support: AttentionCGSupport.UNIFORM_BATCH); setting cudagraph_mode=FULL_DECODE_ONLY
|
||||
(EngineCore pid=112) INFO 09-18 02:57:23 [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=112) ␍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=112) INFO 09-18 02:57:25 [speculator.py:150] Capturing model for speculator...
|
||||
(EngineCore pid=112) ␍Capturing prefill CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]␍Capturing prefill CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 2.15it/s]␍Capturing prefill CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 2.15it/s]
|
||||
(EngineCore pid=112) ␍Capturing decode CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]␍Capturing decode CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 5.63it/s]␍Capturing decode CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 5.62it/s]
|
||||
(EngineCore pid=112) INFO 09-18 02:57:27 [model_runner.py:1057] Graph capturing finished in 3 secs, took 0.14 GiB
|
||||
(EngineCore pid=112) INFO 09-18 02:57:27 [gpu_worker.py:641] Available KV cache memory: 2.78 GiB
|
||||
(EngineCore pid=112) INFO 09-18 02:57:27 [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=112) WARNING 09-18 02:57:27 [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=112) INFO 09-18 02:57:27 [kv_cache_utils.py:2404] GPU KV cache size: 146,622 tokens, Maximum concurrency for 131,072 tokens per request: 1.12x
|
||||
(EngineCore pid=112) INFO 09-18 02:57:27 [kernel_warmup.py:171] JIT kernel warmup starting.
|
||||
(EngineCore pid=112) INFO 09-18 02:57:27 [kernel_warmup.py:184] JIT kernel warmup finished in 0.00s.
|
||||
(EngineCore pid=112) INFO 09-18 02:57:27 [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=112) INFO 09-18 02:57:28 [qwen_vl_triton_warmup.py:98] Warmed M-RoPE Triton kernels.
|
||||
(EngineCore pid=112) INFO 09-18 02:57:28 [mamba_triton_warmup.py:42] Warmed Mamba batch_memcpy_kernel.
|
||||
(EngineCore pid=112) INFO 09-18 02:57:28 [qwen4_exp_qsa_warmup.py:71] Warmed up Qwen4Exp QSA decode kernels: ((1, 1), (2, 1), (3, 1)).
|
||||
(EngineCore pid=112) INFO 09-18 02:57:34 [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=112) INFO 09-18 02:57:34 [kernel_warmup.py:254] Skipping FlashInfer autotune because it is disabled.
|
||||
(EngineCore pid=112) ␍Capturing CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]␍Capturing CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 10.02it/s]
|
||||
(EngineCore pid=112) INFO 09-18 02:57:42 [speculator.py:150] Capturing model for speculator...
|
||||
(EngineCore pid=112) ␍Capturing prefill CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]␍Capturing prefill CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 122.54it/s]
|
||||
(EngineCore pid=112) ␍Capturing decode CUDA graphs (FULL): 0%| | 0/1 [00:00<?, ?it/s]␍Capturing decode CUDA graphs (FULL): 100%|██████████| 1/1 [00:00<00:00, 178.09it/s]
|
||||
(EngineCore pid=112) INFO 09-18 02:57:43 [model_runner.py:1057] Graph capturing finished in 1 secs, took 0.13 GiB
|
||||
(EngineCore pid=112) INFO 09-18 02:57:43 [gpu_worker.py:824] CUDA graph pool memory: 0.13 GiB (actual), 0.14 GiB (estimated), difference: 0.01 GiB (5.8%).
|
||||
(EngineCore pid=112) INFO 09-18 02:57:43 [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=112) INFO 09-18 02:57:43 [jit_monitor.py:84] Kernel JIT monitor activated; monitored JIT compilations during inference will use mode=warn.
|
||||
(EngineCore pid=112) WARNING 09-18 02:57:44 [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=112) INFO 09-18 02:57:44 [core.py:380] init engine (profile, create kv cache, warmup model) took 47.35 s
|
||||
(EngineCore pid=112) INFO 09-18 02:57:44 [kv_cache_utils.py:762] kv cache group sizes [3184, 3184, 3184, 3184, 8, 3184]
|
||||
(EngineCore pid=112) INFO 09-18 02:57:44 [kv_cache_utils.py:763] kv lcm block sizes 3184
|
||||
(EngineCore pid=112) INFO 09-18 02:57:44 [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 02:57:44 [entry.py:132] Supported tasks: ['generate']
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [factories.py:76] Scale-out endpoints are disabled. Set --enable-scale-out to enable them.
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [parser_manager.py:34] "auto" tool choice has been enabled.
|
||||
(APIServer pid=1) [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_interleaved', 'mrope_section'}
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [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 02:57:44 [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 02:57:44 [entry.py:136] Starting vLLM server on http://0.0.0.0:8000
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:60] Available routes are:
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /openapi.json, Methods: GET, HEAD
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /docs, Methods: GET, HEAD
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /docs/oauth2-redirect, Methods: GET, HEAD
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /redoc, Methods: GET, HEAD
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /load, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /version, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /health, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /metrics, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /tokenize, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /detokenize, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/models, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /ping, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /ping, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /invocations, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/chat/completions, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/chat/completions/batch, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/responses, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/responses/{response_id}, Methods: GET
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/responses/{response_id}/cancel, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/completions, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/messages, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /v1/messages/count_tokens, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /generative_scoring, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [launcher.py:69] Route: /scale_elastic_ep, Methods: POST
|
||||
(APIServer pid=1) INFO 09-18 02:57:44 [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: 127.0.0.1:48906 - "GET /health HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:45276 - "GET /health HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:45292 - "GET /v1/models HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:45294 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(EngineCore pid=112) WARNING 09-18 02:57:52 [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=112) WARNING 09-18 02:57:53 [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=112) WARNING 09-18 02:57:53 [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=112) WARNING 09-18 02:57:53 [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=112) WARNING 09-18 02:57:53 [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: 172.21.0.1:45300 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47570 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47586 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO 09-18 02:57:55 [loggers.py:323] Engine 000: Avg prompt throughput: 78.5 tokens/s, Avg generation throughput: 19.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 0.0%, MM cache hit rate: 0.0%
|
||||
(APIServer pid=1) INFO 09-18 02:57:55 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.60, Accepted throughput: 11.82 tokens/s, Drafted throughput: 14.73 tokens/s, Accepted: 130 tokens, Drafted: 162 tokens, Per-position acceptance rate: 0.864, 0.741, Avg Draft acceptance rate: 80.2%
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47598 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) [transformers] Token indices sequence length is longer than the specified maximum sequence length for this model (263582 > 262144). Running this sequence through the model will result in indexing errors
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47602 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47608 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47610 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47624 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47634 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47640 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47650 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47662 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47678 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47688 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47698 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47712 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47716 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47726 - "POST /tokenize HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:47732 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO 09-18 02:58:05 [loggers.py:323] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 9.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 60.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 0.0%
|
||||
(APIServer pid=1) INFO 09-18 02:58:05 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.77, Accepted throughput: 6.20 tokens/s, Drafted throughput: 7.00 tokens/s, Accepted: 62 tokens, Drafted: 70 tokens, Per-position acceptance rate: 0.971, 0.800, Avg Draft acceptance rate: 88.6%
|
||||
(APIServer pid=1) INFO: 172.21.0.1:36086 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:36096 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO 09-18 02:58:15 [loggers.py:323] Engine 000: Avg prompt throughput: 13184.9 tokens/s, Avg generation throughput: 34.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 21.5%, Prefix cache hit rate: 48.3%, MM cache hit rate: 0.0%
|
||||
(APIServer pid=1) INFO 09-18 02:58:15 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.73, Accepted throughput: 21.60 tokens/s, Drafted throughput: 25.00 tokens/s, Accepted: 216 tokens, Drafted: 250 tokens, Per-position acceptance rate: 0.936, 0.792, Avg Draft acceptance rate: 86.4%
|
||||
(APIServer pid=1) INFO: 172.21.0.1:33248 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 127.0.0.1:45376 - "GET /health HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:33262 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO: 172.21.0.1:33272 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
||||
(APIServer pid=1) INFO 09-18 02:58:25 [loggers.py:323] Engine 000: Avg prompt throughput: 17.4 tokens/s, Avg generation throughput: 79.7 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 48.3%, MM cache hit rate: 0.0%
|
||||
(APIServer pid=1) INFO 09-18 02:58:25 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 2.68, Accepted throughput: 49.80 tokens/s, Drafted throughput: 59.20 tokens/s, Accepted: 498 tokens, Drafted: 592 tokens, Per-position acceptance rate: 0.926, 0.757, Avg Draft acceptance rate: 84.1%
|
||||
(APIServer pid=1) INFO 09-18 02:58:35 [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: 48.3%, MM cache hit rate: 0.0%
|
||||
(APIServer pid=1) INFO: 127.0.0.1:60766 - "GET /health HTTP/1.1" 200 OK
|
||||
Reference in New Issue
Block a user