Skip to content

Pull requests: vllm-project/ci-infra

New pull request New
65 Open 434 Closed
65 Open 434 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add observability alerts and dashboard
#501 opened Aug 31, 2026 by bavinainuganti9 • Draft
Fix the AMD template input reference in the README
#496 opened Aug 29, 2026 by Hoiyeuhng Loading…
terraform/aws: add gpu-ci-eks EKS cluster for GPU queue migration
#493 opened Aug 28, 2026 by khluu Member Loading…
tpu-inference/k8s: attach to a dispatched workload without naming its cluster
#489 opened Aug 28, 2026 by theminghuang Collaborator • Draft
1
[DO NOT MERGE UNTIL 2026-09-04] [CI] Retire the tpu-commons half of CI monitoring
#488 opened Aug 27, 2026 by theminghuang Collaborator • Draft
1
Source CI OTel helpers from the vLLM checkout
#480 opened Aug 19, 2026 by khluu Member Loading…
2
Honor mirror.amd.parallelism so NVIDIA sharding cannot multiply AMD mirrors
#473 opened Aug 14, 2026 by khluu Member • Draft
Keep gpu_4_queue at 10 minimum with demand scaling to 40
#471 opened Aug 13, 2026 by khluu Member • Draft
Automatically trace vLLM nightly pytest jobs
#469 opened Aug 12, 2026 by khluu Member • Draft
tpu-inference/k8s: the TPU workload launcher
#467 opened Aug 11, 2026 by theminghuang Collaborator • Draft
1
[CI] Use blobless checkout for image builds
#455 opened Aug 5, 2026 by mgoin Member Loading…
[CI][AMD] Support build-scoped ROCm images
#447 opened Aug 3, 2026 by AndreasKaratzas Member Loading…
Enable fail-fast logit NaN detection in vLLM CI
#444 opened Jul 30, 2026 by tlrmchlsmth Member Loading…
1
[CI] Modernize and harden Agent Stack Kubernetes installer
#441 opened Jul 28, 2026 by mgoin Member • Draft
4 tasks
tpu-inference/k8s: MultiKueue GKE infrastructure for TPU CI
#438 opened Jul 27, 2026 by theminghuang Collaborator • Draft
1
[CI][AMD] Add opt-in Hugging Face cache fallback
#435 opened Jul 23, 2026 by AndreasKaratzas Member Loading…
[CI] Remove the unused ECR cache lookup from pipeline generation
#433 opened Jul 22, 2026 by Hoiyeuhng Loading…
Document the CI environment variables and their defaults
#431 opened Jul 22, 2026 by Hoiyeuhng Loading…
[CI][AMD] Add opt-in Hugging Face Hub retries
#429 opened Jul 22, 2026 by AndreasKaratzas Member • Draft
fix(buildkite): execute trusted pipeline generator from main in boots…
#424 opened Jul 18, 2026 by jcc-google Contributor Loading…
fix(buildkite): disable propagate-environment and filter secrets for …
#423 opened Jul 18, 2026 by jcc-google Contributor Loading…
fix(buildkite): isolate Docker volume host paths for PR builds
#422 opened Jul 18, 2026 by jcc-google Contributor Loading…
fix(buildkite): isolate Kubernetes hostPath volumes for PR builds
#421 opened Jul 18, 2026 by jcc-google Contributor Loading…
Add us-east-1 capacity for gpu_4_queue
#420 opened Jul 15, 2026 by khluu Member • Draft
Add generic native pipeline renderer
#413 opened Jul 10, 2026 by khluu Member Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.