x

Dockerfile

@@ -7,13 +7,17 @@ ENV LOCAL_MODEL_DIR=/opt/model
 # Create necessary directories
 RUN mkdir -p /opt/script /opt/model /config
 
-# Update transformers to support qwen3_5_moe architecture
-RUN pip install --upgrade transformers
-
 # Copy scripts to /opt/script
+COPY scripts/add_qwen3_5_moe_support.py /opt/script/add_qwen3_5_moe_support.py
 COPY scripts/start_vllm.py /opt/script/start-vllm
 COPY benchmarks/run_vllm_bench.py /opt/script/run_vllm_bench.py
 
+# Update vLLM to nightly version for Qwen3.5 support
+RUN pip install --upgrade vllm --extra-index-url https://wheels.vllm.ai/nightly
+
+# Add qwen3_5_moe support to Transformers
+RUN python3 /opt/script/add_qwen3_5_moe_support.py
+
 # Note: config.json should be mounted at runtime via docker-compose.yml
 
 # Make scripts executable