LocalAI/.github/workflows
LocalAI [bot] 35f6db8c76
ci: split backend-jobs into single-arch and multi-arch matrices (#9746)
Symptom (run 25612992409): backend-merge-jobs failed with
"quay.io/go-skynet/local-ai-backends@sha256:fdbd93ca...: not found"
even though the per-arch build for -cpu-llama-cpp pushed that exact
digest 14h31m earlier.

Root cause: backend-merge-jobs was gated on the WHOLE backend-jobs
matrix (`needs: backend-jobs`). The multi-arch -cpu-llama-cpp legs
finished within 30 min, but a single-arch CUDA-12-llama-cpp slot in
the same matrix queued for ~8h (max-parallel: 8 throttle) and then
took ~6h to build cold. By the time it freed the merge to run, quay's
GC had reaped the per-arch digests pushed by the fast multi-arch legs
the day before.

Fix: split the linux backend matrix in two.

  backend-jobs-multiarch  - entries with `platform-tag` set (paired
    per-arch legs that feed backend-merge-jobs).
  backend-jobs-singlearch - entries without `platform-tag` (heavy
    standalone builds: CUDA, ROCm, Intel oneAPI, vLLM, sglang, etc.).

backend-merge-jobs now `needs:` only backend-jobs-multiarch. The
multi-arch matrix completes in ~2-3h, well inside quay's GC window.
Heavy single-arch entries keep running independently with no merge
dependency.

scripts/changed-backends.js gains a splitByArch() helper that
partitions filtered entries by whether `platform-tag` is set, and
emits matrix-singlearch + matrix-multiarch + has-backends-singlearch
+ has-backends-multiarch outputs (replacing the previous combined
matrix / has-backends pair). Applied in both the full-matrix and
filtered-matrix code paths. Smoke test: 199 single-arch + 72 multi-
arch + 35 darwin = 271 total entries; 36 merge-matrix entries
(one per multi-arch backend pair). Matches expectation.

Local `make backends/<name>` is unaffected — the script's outputs
only feed CI workflow matrices.

Assisted-by: Claude:claude-opus-4-7

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-05-10 18:15:53 +02:00
..
disabled chore(ci): disable CI actions 2026-03-02 14:48:00 +01:00
backend.yml ci: split backend-jobs into single-arch and multi-arch matrices (#9746) 2026-05-10 18:15:53 +02:00
backend_build.yml ci: refactor llama-cpp variant Dockerfiles to consume prebuilt base-grpc images (PR 2/2) (#9738) 2026-05-10 00:03:52 +02:00
backend_build_darwin.yml ci(darwin): force-link brew formulas after cache restore 2026-05-09 20:41:03 +00:00
backend_merge.yml ci: phase 1-3 of GHA free tier migration (path filter, multi-arch split prep, /mnt disk relief) (#9726) 2026-05-08 23:43:41 +02:00
backend_pr.yml ci: split backend-jobs into single-arch and multi-arch matrices (#9746) 2026-05-10 18:15:53 +02:00
base-images.yml ci(base-images): also trigger rebuild on .docker/install-base-deps.sh changes 2026-05-09 22:30:46 +00:00
build-test.yaml feat(ci): allow routing apt traffic through an alternate Ubuntu mirror (#9650) 2026-05-03 23:50:13 +02:00
bump-inference-defaults.yml chore(deps): bump peter-evans/create-pull-request from 7 to 8 (#9114) 2026-03-24 08:50:50 +01:00
bump_deps.yaml Change vibevoice.cpp repository reference 2026-05-09 10:30:11 +02:00
bump_docs.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
checksum_checker.yaml feat(ci): allow routing apt traffic through an alternate Ubuntu mirror (#9650) 2026-05-03 23:50:13 +02:00
deploy-explorer.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
gallery-agent.yaml Change cron schedule to run every 12 hours 2026-04-25 18:38:28 +02:00
generate_intel_image.yaml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
gh-pages.yml chore(deps): bump actions/upload-pages-artifact from 4 to 5 (#9337) 2026-04-13 21:53:47 +02:00
image-pr.yml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
image.yml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
image_build.yml ci: finish GHA free-tier migration (per-arch fan-out, image splits, retire self-hosted, fix provenance) (#9730) 2026-05-09 09:37:00 +02:00
image_merge.yml ci: finish GHA free-tier migration (per-arch fan-out, image splits, retire self-hosted, fix provenance) (#9730) 2026-05-09 09:37:00 +02:00
lint.yml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
notify-releases.yaml fix(api)!: Stop model prior to deletion (#8422) 2026-02-06 09:22:10 +01:00
release.yaml feat(ci): allow routing apt traffic through an alternate Ubuntu mirror (#9650) 2026-05-03 23:50:13 +02:00
secscan.yaml Revert "chore(deps): bump securego/gosec from 2.22.9 to 2.22.11" (#7789) 2025-12-30 09:58:13 +01:00
stalebot.yml chore(deps): bump actions/stale from 10.1.1 to 10.2.0 (#8633) 2026-02-23 23:27:20 +01:00
test-extra.yml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
test.yml ci: drop paths-ignore from test.yml and tests-e2e.yml 2026-05-09 09:23:51 +00:00
tests-aio.yml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
tests-e2e.yml ci: drop paths-ignore from test.yml and tests-e2e.yml 2026-05-09 09:23:51 +00:00
tests-ui-e2e.yml ci(concurrency): make cancel-in-progress event-aware, group by sha on push 2026-05-09 08:30:55 +00:00
update_swagger.yaml feat(ci): allow routing apt traffic through an alternate Ubuntu mirror (#9650) 2026-05-03 23:50:13 +02:00
yaml-check.yml chore(backend gallery): add description for remaining backends (#5679) 2025-06-17 22:21:44 +02:00