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

Fix docker python version (#2845)

Browse Source
This commit is contained in:
Nikola Borisov 2024-02-14 10:17:57 -08:00 committed by GitHub
parent 7e45107f51
commit 87069ccf68
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
Dockerfile
View File

@ -4,21 +4,8 @@
#################### BASE BUILD IMAGE #################### #################### BASE BUILD IMAGE ####################
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS dev FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS dev
# Set the DEBIAN_FRONTEND variable to noninteractive to avoid interactive prompts
ENV DEBIAN_FRONTEND=noninteractive
# Preconfigure tzdata for US Central Time (build running in us-central-1 but this really doesn't matter.)
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Chicago' | debconf-set-selections
# We install an older version of python here for testing to make sure vllm works with older versions of Python.
# For the actual openai compatible server, we will use the latest version of Python.
RUN apt-get update -y \ RUN apt-get update -y \
&& apt-get install -y software-properties-common \ && apt-get install -y python3-pip git
&& add-apt-repository ppa:deadsnakes/ppa -y \
&& apt-get update -y \
&& apt-get install -y python3.8 python3.8-dev python3.8-venv python3-pip git \
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.8 1
# Workaround for https://github.com/openai/triton/issues/2507 and # Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully # https://github.com/pytorch/pytorch/issues/107960 -- hopefully
@ -88,8 +75,10 @@ RUN --mount=type=cache,target=/root/.cache/pip VLLM_USE_PRECOMPILED=1 pip instal
#################### RUNTIME BASE IMAGE #################### #################### RUNTIME BASE IMAGE ####################
# use CUDA base as CUDA runtime dependencies are already installed via pip # We used base cuda image because pytorch installs its own cuda libraries.
FROM nvidia/cuda:12.1.0-base-ubuntu22.04 AS vllm-base # However cupy depends on cuda libraries so we had to switch to the runtime image
# In the future it would be nice to get a container with pytorch and cuda without duplicating cuda
FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04 AS vllm-base
# libnccl required for ray # libnccl required for ray
RUN apt-get update -y \ RUN apt-get update -y \

2
requirements.txt
View File

@ -12,4 +12,4 @@ pydantic >= 2.0 # Required for OpenAI server.
aioprometheus[starlette] aioprometheus[starlette]
pynvml == 11.5.0 pynvml == 11.5.0
triton >= 2.1.0 triton >= 2.1.0
cupy-cuda12x == 12.3.0 # Required for CUDA graphs. CUDA 11.8 users should install cupy-cuda11x instead. cupy-cuda12x == 12.1.0 # Required for CUDA graphs. CUDA 11.8 users should install cupy-cuda11x instead.