@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / e221910e77
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 17, 04:15 UTC

add hf_transfer to requirements.txt (#3031)

Ronan McGovern committed Mar 13, 2024 at 06:33 UTC e221910e77087743a50560e4ae69c3c2a12beb53
1 file changed +1 -1
Dockerfile
+1 -1
@@ -96,7 +96,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
96 FROM vllm-base AS vllm-openai
97 # install additional dependencies for openai api server
98 RUN --mount=type=cache,target=/root/.cache/pip \
99 - pip install accelerate
99 + pip install accelerate hf_transfer
100
101 COPY --from=build /workspace/vllm/*.so /workspace/vllm/
102 COPY vllm vllm