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