Enable validated prefix caching and record DGX Spark optimization benchmarks

2026-09-17 22:09:58 +08:00
parent 5f3030260e
commit 1e2f48d1a4
28 changed files with 707 additions and 8 deletions
@@ -1,7 +1,7 @@
 name: qwen38-flash-dgx-spark
 services:
  vllm:
-    image: local/qwen38-flash-spark:nightly-0bfc7a15
+    image: local/qwen38-flash-spark:prefix-eager-0bfc7a15
    build:
      context: .
      args:
@@ -45,7 +45,7 @@ services:
        --dtype bfloat16 --kv-cache-dtype auto
        --gpu-memory-utilization ${GPU_MEMORY_UTILIZATION:-0.80}
        --max-model-len 262144 --max-num-seqs ${MAX_NUM_SEQS:-4} --max-num-batched-tokens 2048
-        --enable-chunked-prefill --no-enable-prefix-caching
+        --enable-chunked-prefill --enable-prefix-caching
        --speculative-config '{"method":"mtp","num_speculative_tokens":2}'
        --enforce-eager --no-enable-flashinfer-autotune
        --load-format safetensors