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 11, 13:45 UTC
[CI/Build] Add x86 CPU wheel release pipeline (#28848)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Dec 13, 2025 at 03:21 UTC
9693dd0fe382e10abf239e33dbb1707cebc18ff9
1 file changed
+14
.buildkite/release-pipeline.yaml
+14
@@ -71,6 +71,20 @@ steps:
71
env:
72
DOCKER_BUILDKIT: "1"
73
74
+ # x86 CPU wheel build
75
+ - label: "Build x86 CPU wheel"
76
+ depends_on: ~
77
+ id: build-wheel-x86-cpu
78
+ agents:
79
+ queue: cpu_queue_postmerge
80
+ commands:
81
+ - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_CPU_AVX512BF16=true --build-arg VLLM_CPU_AVX512VNNI=true --build-arg VLLM_CPU_AMXBF16=true --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
82
+ - "mkdir artifacts"
83
+ - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
84
+ - "bash .buildkite/scripts/upload-wheels.sh manylinux_2_35"
85
+ env:
86
+ DOCKER_BUILDKIT: "1"
87
+
88
# Build release images (12.9)
89
- label: "Build release image (x86)"
90
depends_on: ~