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, 05:45 UTC
[ci/build] Change queue name for Release jobs (#10875)
Kevin H. Luu committed
Dec 3, 2024 at 23:02 UTC
fa2dea61df9bb3fa3dbd081f42f464c45e3db5b2
1 file changed
+2
-2
.buildkite/release-pipeline.yaml
+2
-2
@@ -1,7 +1,7 @@
1
steps:
2
- label: "Build wheel - CUDA 12.1"
3
agents:
4
- queue: cpu_queue
4
+ queue: cpu_queue_postmerge
5
commands:
6
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.1.0 --tag vllm-ci:build-image --target build --progress plain ."
7
- "mkdir artifacts"
@@ -18,7 +18,7 @@ steps:
18
- label: "Build wheel - CUDA 11.8"
19
# depends_on: block-build-cu118-wheel
20
agents:
21
- queue: cpu_queue
21
+ queue: cpu_queue_postmerge
22
commands:
23
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=11.8.0 --tag vllm-ci:build-image --target build --progress plain ."
24
- "mkdir artifacts"