xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 05:04:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[ci] Use sccache to build images (#5419)

Browse Source 
Signed-off-by: kevin <kevin@anyscale.com>
This commit is contained in:
Kevin H. Luu 2024-06-12 17:58:12 -07:00 committed by GitHub
parent ea3890a5f0
commit 916d219d62
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 22 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/test-template-aws.j2
View File

@ -7,7 +7,7 @@ steps:
queue: cpu_queue
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "docker build --build-arg max_jobs=16 --tag {{ docker_image }} --target test --progress plain ."
- "docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --tag {{ docker_image }} --target test --progress plain ."
- "docker push {{ docker_image }}"
env:
DOCKER_BUILDKIT: "1"

22
Dockerfile
View File

@ -10,7 +10,7 @@
FROM nvidia/cuda:12.4.1-devel-ubuntu22.04 AS dev
RUN apt-get update -y \
&& apt-get install -y python3-pip git
&& apt-get install -y python3-pip git curl sudo
# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
@ -70,10 +70,28 @@ ENV NVCC_THREADS=$nvcc_threads
# make sure punica kernels are built (for LoRA)
ENV VLLM_INSTALL_PUNICA_KERNELS=1
ARG USE_SCCACHE
# if USE_SCCACHE is set, use sccache to speed up compilation
RUN --mount=type=cache,target=/root/.cache/pip \
if [ "$USE_SCCACHE" = "1" ]; then \
echo "Installing sccache..." \
&& curl -L -o sccache.tar.gz https://github.com/mozilla/sccache/releases/download/v0.8.1/sccache-v0.8.1-x86_64-unknown-linux-musl.tar.gz \
&& tar -xzf sccache.tar.gz \
&& sudo mv sccache-v0.8.1-x86_64-unknown-linux-musl/sccache /usr/bin/sccache \
&& rm -rf sccache.tar.gz sccache-v0.8.1-x86_64-unknown-linux-musl \
&& export SCCACHE_BUCKET=vllm-build-sccache \
&& export SCCACHE_REGION=us-west-2 \
&& sccache --show-stats \
&& python3 setup.py bdist_wheel --dist-dir=dist \
&& sccache --show-stats; \
fi
ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/pip \
python3 setup.py bdist_wheel --dist-dir=dist
if [ "$USE_SCCACHE" != "1" ]; then \
python3 setup.py bdist_wheel --dist-dir=dist; \
fi
# check the size of the wheel, we cannot upload wheels larger than 100MB
COPY .buildkite/check-wheel-size.py check-wheel-size.py

2
setup.py
View File

@ -140,6 +140,7 @@ class cmake_build_ext(build_ext):
cmake_args += [
'-DCMAKE_CXX_COMPILER_LAUNCHER=sccache',
'-DCMAKE_CUDA_COMPILER_LAUNCHER=sccache',
'-DCMAKE_C_COMPILER_LAUNCHER=sccache',
]
elif is_ccache_available():
cmake_args += [
@ -171,7 +172,6 @@ class cmake_build_ext(build_ext):
else:
# Default build tool to whatever cmake picks.
build_tool = []
subprocess.check_call(
['cmake', ext.cmake_lists_dir, *build_tool, *cmake_args],
cwd=self.build_temp)