hailin
/
vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

.

This commit is contained in:
hailin 2025-08-04 12:45:16 +08:00
parent fc62ba578c
commit 62ee2cade3
1 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
Dockerfile
View File

@ -401,34 +401,34 @@
# RUN mv mkdocs.yaml test_docs/
# #################### TEST IMAGE ####################
# #################### OPENAI API SERVER ####################
# # base openai image with additional requirements, for any subsequent openai-style images
# FROM vllm-base AS vllm-openai-base
# ARG TARGETPLATFORM
# ARG INSTALL_KV_CONNECTORS=false
#################### OPENAI API SERVER ####################
# base openai image with additional requirements, for any subsequent openai-style images
FROM vllm-base AS vllm-openai-base
ARG TARGETPLATFORM
ARG INSTALL_KV_CONNECTORS=false
# ARG PIP_INDEX_URL UV_INDEX_URL
# ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
# # This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# # Reference: https://github.com/astral-sh/uv/pull/1694
# ENV UV_HTTP_TIMEOUT=500
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694
ENV UV_HTTP_TIMEOUT=500
# COPY ./vllm_v0.10.0/requirements/kv_connectors.txt requirements/kv_connectors.txt
COPY ./vllm_v0.10.0/requirements/kv_connectors.txt requirements/kv_connectors.txt
# # install additional dependencies for openai api server
# RUN --mount=type=cache,target=/root/.cache/uv \
# if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then \
# uv pip install --system -r requirements/kv_connectors.txt; \
# fi; \
# if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
# BITSANDBYTES_VERSION="0.42.0"; \
# else \
# BITSANDBYTES_VERSION="0.46.1"; \
# fi; \
# uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then \
uv pip install --system -r requirements/kv_connectors.txt; \
fi; \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
BITSANDBYTES_VERSION="0.42.0"; \
else \
BITSANDBYTES_VERSION="0.46.1"; \
fi; \
uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]
# ENV VLLM_USAGE_SOURCE production-docker-image
ENV VLLM_USAGE_SOURCE production-docker-image
# # define sagemaker first, so it is not default from `docker build`
# FROM vllm-openai-base AS vllm-sagemaker