[CI]init intel ci dispatch in buildkite folder#1721
Conversation
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
|
@tjtanaa , need help here. But not sure how it works in OMNI project. |
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
9e19b9b to
409f9da
Compare
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
409f9da to
dd03158
Compare
|
@khluu @hsliuustc0106 , I think the PR should be working now. CI node is registered to buildkite agent queue. Wondering if we can get this PR merged and test out? |
|
Should this PR wait for #1340? |
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
|
Please let me know if you need an extra Buildkite pipeline for intel CI tests. |
| agents: | ||
| queue: "cpu_queue_premerge" | ||
|
|
||
| # L5 Test |
There was a problem hiding this comment.
L5 tests mean stability & reliability tests as mentioned in the table in https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/CI_5levels/#document-overview. Comment like # Intel tests is fine for your case.
There was a problem hiding this comment.
Got it, I have removed changes in pipeline.yml for now. I think with a separate buildkite pipeline makes more sense.
|
Will this PR not introduce any tests run on the XPU? |
yes, this PR is to confirm dispatch works, and xpu CI is added with: #1340 |
|
Good. I saw this PR yesterday and left some comments about pytest marks. Please consider it. If you prefer instant communication, you can find me in the WeChat group. |
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
|
@congw729 , Thanks, |
|
Thanks, @gcanlin |
Not really sure. @tjtanaa Do you know anything about it? |
Let me check, if the buildkite commands are setup correctly, it should be able to invoke the bash script from this PR branch. We don't have to wait until the bash script landed on main |
|
This PR has to be merged before triggering the INTEL CI pipeline, please take a look @hsliuustc0106 @Gaohan123 |
|
@xuechendi @congw729 I helped trigger the build to validate this PR https://buildkite.com/vllm/vllm-omni-intel-ci/builds/8/steps/canvas |
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
|
@Gaohan123 @hsliuustc0106 ,
|
Signed-off-by: Chendi Xue <chendi.xue@intel.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>



PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.
Purpose
Add CI dispatch
[x] add 'intel-gpu-omni' queue in buildkite CI cluster => Done

[x] register buildkite agent to 'intel-gpu-omni'
Current design is:
.buildkite/pipeline.yaml->
.buildkite/bootstrap-intel-omni.sh->
pipeline-intel.yml->
bash .buildkite/scripts/hardware_ci/run-xpu-test.shNote:
bootstrap-intel-omni.sh: used to check if we need to skip CI for pipeline-intel.yamlpipeline-intel.yaml: actual steps for CI- now, single step to trigger an all-in-one file;
- Future, multiple steps to build docker in AWS and test in Intel-gpu-omni agents)
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model. Please runmkdocs serveto sync the documentation editions to./docs.BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)