@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / c6f2485c82
Fork 0

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