Update Dockerfile

Dockerfile

@@ -7,6 +7,10 @@ ENV OMP_NUM_THREADS=1
 ENV VLLM_USE_TRITON_FLASH_ATTN=0
 ENV VLLM_ATTENTION_BACKEND=XFORMERS
 
+# e.g. install the `audio` optional dependencies
+# NOTE: Make sure the version of vLLM matches the base image!
+RUN uv pip install --system vllm[audio]==0.10.0
+
 # Create a user and group with the specified ID
 RUN groupadd -r myuser --gid 1000 && useradd -r -g myuser --uid 1000 myuser
 
@@ -15,10 +19,6 @@ USER myuser
 
 RUN mkdir -p /tmp/.cache/huggingface
 
-# e.g. install the `audio` optional dependencies
-# NOTE: Make sure the version of vLLM matches the base image!
-RUN uv pip install --system vllm[audio]==0.10.0
-
 ENTRYPOINT ["/bin/bash",  "-c", "vllm serve meta-llama/Llama-3.2-3B-Instruct --task generate --revision 0cb88a4f764b7a12671c53f0838cd831a0843b95 --code-revision 0cb88a4f764b7a12671c53f0838cd831a0843b95 --tokenizer-revision 0cb88a4f764b7a12671c53f0838cd831a0843b95 --seed 42 --host 0.0.0.0 --port 7860 --max-num-batched-tokens 32768 --max-model-len 32768 --dtype float16 --enforce-eager --gpu-memory-utilization 0.9 --enable-prefix-caching --disable-log-requests --trust-remote-code"]
 
 # # FROM nvidia/cuda:12.1.0-cudnn8-runtime-ubuntu22.04