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 17, 04:15 UTC
Update dockerfile with ModelScope support (#3429)
ifsheldon committed
Mar 20, 2024 at 01:54 UTC
c614cfee5861e5715a023fa501e432d4acf910fe
1 file changed
+1
-1
Dockerfile
+1
-1
@@ -122,7 +122,7 @@ RUN --mount=type=bind,from=flash-attn-builder,src=/usr/src/flash-attention-v2,ta
122
FROM vllm-base AS vllm-openai
123
# install additional dependencies for openai api server
124
RUN --mount=type=cache,target=/root/.cache/pip \
125
- pip install accelerate hf_transfer
125
+ pip install accelerate hf_transfer modelscope
126
127
COPY --from=build /workspace/vllm/*.so /workspace/vllm/
128
COPY vllm vllm