From 9115672bb8436d68a77493ba5d472195d7418700 Mon Sep 17 00:00:00 2001 From: SZCJW <792430652@qq.com> Date: Fri, 27 Mar 2026 01:24:15 +0800 Subject: [PATCH] xx --- Dockerfile | 4 ++-- scripts/start_vllm.py | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/Dockerfile b/Dockerfile index 7200897..812d256 100644 --- a/Dockerfile +++ b/Dockerfile @@ -16,8 +16,8 @@ COPY benchmarks/run_vllm_bench.py /opt/script/run_vllm_bench.py # Make scripts executable RUN chmod +x /opt/script/start-vllm -# Create symlink for backward compatibility -RUN ln -sf /opt/script/start-vllm /usr/local/bin/start-vllm +# Replace the container's start-vllm with our improved version +RUN cp /opt/script/start-vllm /usr/local/bin/start-vllm # Set working directory WORKDIR /opt diff --git a/scripts/start_vllm.py b/scripts/start_vllm.py index 221e9d5..96952c4 100644 --- a/scripts/start_vllm.py +++ b/scripts/start_vllm.py @@ -138,8 +138,11 @@ def nuke_vllm_cache(): print(f" Failed: {e}") def configure_and_launch(model_idx, gpu_count): + print(f"DEBUG: configure_and_launch called with model_idx={model_idx}, gpu_count={gpu_count}") model_id = MODELS_TO_RUN[model_idx] config = MODEL_TABLE[model_id] + print(f"DEBUG: model_id={model_id}") + print(f"DEBUG: LOCAL_MODEL_DIR={LOCAL_MODEL_DIR}") # Determine whether we have a local copy to serve. Try multiple fallbacks: # 1) LOCAL_MODEL_DIR//