Temporarily disable speculative decoding to test base model

2026-08-08 17:28:00 -07:00
parent 9d00f36d2b
commit c530e16880
1 changed files with 1 additions and 1 deletions
@@ -22,7 +22,7 @@ exec docker run --rm --name vllm-awq-qwen36-dflash-ampere \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    vllm/vllm-openai:nightly "${MODEL}" \
    --served-model-name "frank-default-small" \
-    --speculative-config '{"method": "dflash", "model": "z-lab/Qwen3.6-35B-A3B-DFlash", "num_speculative_tokens": 4}' \
+    # --speculative-config '{"method": "dflash", "model": "z-lab/Qwen3.6-35B-A3B-DFlash", "num_speculative_tokens": 4}' \
    --max-num-seqs 2 \
    --max-model-len 32768 \
    --tensor-parallel-size 1 \