A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 15:45 UTC
[[Misc]] Add extra deps for openai server image (#8792)
Jee Jee Li committed
Sep 26, 2024 at 00:35 UTC
c6f2485c823b5cd76cca70798e653c6eadb811de
1 file changed
+1
-1
Dockerfile
+1
-1
@@ -202,7 +202,7 @@ FROM vllm-base AS vllm-openai
202
203
# install additional dependencies for openai api server
204
RUN --mount=type=cache,target=/root/.cache/pip \
205
- pip install accelerate hf_transfer 'modelscope!=1.15.0'
205
+ pip install accelerate hf_transfer 'modelscope!=1.15.0' bitsandbytes>=0.44.0 timm==0.9.10
206
207
ENV VLLM_USAGE_SOURCE production-docker-image
208