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>
This commit is contained in:
LocalAI [bot]
2026-05-10 18:15:53 +02:00
committed by GitHub
parent 6113e5a4d0
commit 35f6db8c76
3 changed files with 129 additions and 25 deletions

View File

@@ -163,14 +163,29 @@ function computeMergeMatrix(entries) {
return { include };
}
// Split a list of linux matrix entries into single-arch (no platform-tag) and
// multi-arch (platform-tag set, paired with a sibling entry sharing the same
// tag-suffix). The two are run as separate matrix jobs so backend-merge-jobs
// can `needs:` only the multi-arch one — slow single-arch builds (CUDA, ROCm,
// vLLM, etc.) don't block manifest assembly while their per-arch counterparts'
// untagged digests sit on quay long enough to be GC'd.
function splitByArch(entries) {
const multiarch = entries.filter(e => e['platform-tag']);
const singlearch = entries.filter(e => !e['platform-tag']);
return { multiarch, singlearch };
}
function emitFullMatrix() {
const { multiarch, singlearch } = splitByArch(includes);
const mergeMatrix = computeMergeMatrix(includes);
const hasMerges = mergeMatrix.include.length > 0 ? 'true' : 'false';
fs.appendFileSync(process.env.GITHUB_OUTPUT, `run-all=true\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends=true\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch=${singlearch.length > 0 ? 'true' : 'false'}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-multiarch=${multiarch.length > 0 ? 'true' : 'false'}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-darwin=true\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges=${hasMerges}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix=${JSON.stringify({ include: includes })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch=${JSON.stringify({ include: singlearch })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-multiarch=${JSON.stringify({ include: multiarch })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-darwin=${JSON.stringify({ include: includesDarwin })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix=${JSON.stringify(mergeMatrix)}\n`);
for (const backend of allBackendPaths.keys()) {
@@ -195,19 +210,24 @@ function emitFilteredMatrix(changedFiles) {
console.log("Filtered files:", filtered);
console.log("Filtered files Darwin:", filteredDarwin);
const hasBackends = filtered.length > 0 ? 'true' : 'false';
const { multiarch, singlearch } = splitByArch(filtered);
const hasBackendsSinglearch = singlearch.length > 0 ? 'true' : 'false';
const hasBackendsMultiarch = multiarch.length > 0 ? 'true' : 'false';
const hasBackendsDarwin = filteredDarwin.length > 0 ? 'true' : 'false';
console.log("Has backends?:", hasBackends);
console.log("Has single-arch backends?:", hasBackendsSinglearch);
console.log("Has multi-arch backends?:", hasBackendsMultiarch);
console.log("Has Darwin backends?:", hasBackendsDarwin);
const mergeMatrix = computeMergeMatrix(filtered);
const hasMerges = mergeMatrix.include.length > 0 ? 'true' : 'false';
fs.appendFileSync(process.env.GITHUB_OUTPUT, `run-all=false\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends=${hasBackends}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch=${hasBackendsSinglearch}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-multiarch=${hasBackendsMultiarch}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-darwin=${hasBackendsDarwin}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges=${hasMerges}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix=${JSON.stringify({ include: filtered })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch=${JSON.stringify({ include: singlearch })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-multiarch=${JSON.stringify({ include: multiarch })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-darwin=${JSON.stringify({ include: filteredDarwin })}\n`);
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix=${JSON.stringify(mergeMatrix)}\n`);