feat(cpu-gguf): keep-f16 resident loader (QUANT-GGUF-KEEPQ-LOADER L6)… #839
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: ci | |
| on: | |
| push: | |
| branches: [main] | |
| pull_request: | |
| jobs: | |
| agent-record: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Canonical roadmap tables and links are consistent | |
| run: | | |
| python3 scripts/check-agent-record.py | |
| python3 tests/scripts/test_agent_record.py | |
| python3 tests/scripts/test_doc_checkpoint.py | |
| documentation-checkpoint: | |
| # Gate: every code/test/benchmark/spike/lifecycle iteration refreshes both | |
| # user-facing status surfaces in that same commit, including void attempts. | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Every feature checkpoint updates README and BENCHMARKS | |
| env: | |
| EVENT_NAME: ${{ github.event_name }} | |
| PR_BASE: ${{ github.event.pull_request.base.sha }} | |
| PR_HEAD: ${{ github.event.pull_request.head.sha }} | |
| PUSH_BASE: ${{ github.event.before }} | |
| PUSH_HEAD: ${{ github.sha }} | |
| run: | | |
| set -eu | |
| if [ "$EVENT_NAME" = "pull_request" ]; then | |
| base="$PR_BASE" | |
| head="$PR_HEAD" | |
| else | |
| base="$PUSH_BASE" | |
| head="$PUSH_HEAD" | |
| fi | |
| python3 scripts/check-doc-checkpoint.py --base "$base" --head "$head" | |
| commit-protocol-tag: | |
| # Gate: every NEW commit must carry the FOLLOWING_AGENTS_PROTOCOL trailer, | |
| # asserting the contributor read AGENTS.md. See .agents/ai-coding-assistants.md. | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Every new commit carries FOLLOWING_AGENTS_PROTOCOL | |
| run: | | |
| set -eu | |
| if [ "${{ github.event_name }}" = "pull_request" ]; then | |
| base="${{ github.event.pull_request.base.sha }}" | |
| head="${{ github.event.pull_request.head.sha }}" | |
| else | |
| base="${{ github.event.before }}" | |
| head="${{ github.sha }}" | |
| fi | |
| # Enforce on the FIRST-PARENT mainline (the commits the submitter | |
| # directly lands on the target branch, incl. merge commits which are | |
| # skipped below). Merged-in feature-branch commits are owned by the | |
| # submitter via the merge and are not re-checked here. | |
| # New branch / unreachable base (all-zero SHA): only check the tip commit. | |
| if ! git cat-file -e "${base}^{commit}" 2>/dev/null; then | |
| commits="$head" | |
| else | |
| commits="$(git rev-list --first-parent "${base}..${head}")" | |
| fi | |
| fail=0 | |
| for c in $commits; do | |
| # Skip merge commits (>1 parent) — they are not authored content. | |
| if [ "$(git rev-list --parents -n1 "$c" | wc -w)" -gt 2 ]; then continue; fi | |
| if ! git log -1 --format=%B "$c" | grep -q 'FOLLOWING_AGENTS_PROTOCOL'; then | |
| echo "::error::commit $c is missing the FOLLOWING_AGENTS_PROTOCOL trailer — read AGENTS.md" | |
| git log -1 --oneline "$c" | |
| fail=1 | |
| fi | |
| done | |
| if [ "$fail" -ne 0 ]; then | |
| echo "One or more commits lack FOLLOWING_AGENTS_PROTOCOL. See AGENTS.md / .agents/ai-coding-assistants.md." | |
| exit 1 | |
| fi | |
| echo "OK: all new commits carry FOLLOWING_AGENTS_PROTOCOL." | |
| cuda-arch-features: | |
| # Configure-tier assertions on the CUDA per-arch FEATURE TABLE. Needs neither | |
| # a CUDA toolkit nor a GPU: it drives cmake/CudaArchFeatures.cmake directly, | |
| # so the resolution that decides which architectures get fp4-mma / | |
| # cutlass-nvfp4 / cutlass-fp8 / marlin-nvfp4 / fa2 (whose historical failure | |
| # mode was a SILENT capability drop) is checked on every push. | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: CUDA feature table resolves per architecture | |
| run: cmake -P cmake/CudaArchFeaturesTest.cmake | |
| device-leakage: | |
| # The DSR RATCHET (work row `S1` of .agents/specs/accelerator-seam-audit.md). | |
| # Counts device-specific references in `src/vllm/` + `include/vllm/` — the | |
| # layer that is supposed to be device-agnostic — and fails on ANY increase | |
| # over scripts/device-leakage-baseline.json. A reduction must lower the | |
| # baseline in the SAME commit, so the number can only ever move down. | |
| # | |
| # It exists because the audit re-measured the leakage and found it had DRIFTED | |
| # UPWARD with no bad commit: DeepSeek-V2, Qwen3-Coder and the attention-registry | |
| # work each added a device test in passing. Leakage grows silently under | |
| # well-executed work, which is a job for a ratchet, not a cleanup. | |
| # | |
| # Needs neither a CUDA toolkit nor a GPU — pure static analysis, like the | |
| # cuda-arch-features job above. The mutation suite proves the checker actually | |
| # catches a planted leak; an unpoliced checker is worse than none. | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Shared-layer device leakage does not grow (DSR ratchet) | |
| run: | | |
| python3 scripts/check-device-leakage.py --report | |
| python3 tests/scripts/test_device_leakage.py | |
| build-test-cpu: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Configure | |
| run: cmake -S . -B build -DVLLM_CPP_BUILD_TESTS=ON | |
| - name: Build | |
| # Bounded parallelism: a bare `-j` lets Make link ALL test executables at | |
| # once, which OOM-kills the runner (ld signal 9) during the parallel link. | |
| run: cmake --build build -j 2 | |
| - name: Test | |
| run: ctest --test-dir build --output-on-failure |