@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f1e72cc19a
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, 23:15 UTC

[BugFix] exclude version 1.15.0 for modelscope (#5668)

zhyncs committed Jun 22, 2024 at 03:15 UTC f1e72cc19a21928400b63743d5fe164ec8ed30e8
1 file changed +1 -1
Dockerfile
+1 -1
@@ -172,7 +172,7 @@ FROM vllm-base AS vllm-openai
172
173 # install additional dependencies for openai api server
174 RUN --mount=type=cache,target=/root/.cache/pip \
175 - pip install accelerate hf_transfer modelscope
175 + pip install accelerate hf_transfer 'modelscope!=1.15.0'
176
177 ENV VLLM_USAGE_SOURCE production-docker-image
178