diff --git a/.github/workflows/studio-windows-inference-smoke.yml b/.github/workflows/studio-windows-inference-smoke.yml index b33b6f9563..13bd8e58e2 100644 --- a/.github/workflows/studio-windows-inference-smoke.yml +++ b/.github/workflows/studio-windows-inference-smoke.yml @@ -73,15 +73,29 @@ jobs: with: python-version: '3.12' - - name: Cache HF_HOME for ${{ env.GGUF_REPO }} + # Split restore + save (rather than the one-step actions/cache) so a + # transient restore-side failure does not kill the whole job. v5 has a + # known flake where it logs "Cache hit for: " and then exits + # non-zero without actually extracting the archive (see + # actions/cache#1621 and github community discussion #163260). + # continue-on-error on restore masks that failure so the Prime step + # below can re-download from HF and the job keeps running. Save then + # populates the cache key on a real miss only; cache keys are + # immutable, so a corrupted cached entry persists until the -v1 + # suffix below is bumped. + - name: Restore HF_HOME cache for ${{ env.GGUF_REPO }} id: cache-hf - uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + continue-on-error: true with: path: hf-cache key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v1 - name: Prime HF_HOME with the GGUF - if: steps.cache-hf.outputs.cache-hit != 'true' + id: prime-hf + # Run on a real cache miss AND on the silent-restore-failure mode + # described above (outcome != success). + if: steps.cache-hf.outputs.cache-hit != 'true' || steps.cache-hf.outcome != 'success' env: HF_TOKEN: ${{ secrets.HF_TOKEN }} run: | @@ -90,6 +104,16 @@ jobs: HF_HUB_ENABLE_HF_TRANSFER=1 \ hf download "$GGUF_REPO" "$GGUF_FILE" + - name: Save HF_HOME cache for ${{ env.GGUF_REPO }} + # Only write a fresh cache entry when we actually rebuilt the + # directory (Prime ran and succeeded). Skipping when Prime is + # skipped avoids "already exists" save warnings on the happy path. + if: always() && steps.prime-hf.outcome == 'success' + uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + with: + path: hf-cache + key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v1 + - name: Pre-install Windows tweaks (npm 11 + Defender exclusions) shell: pwsh # See studio-windows-update-smoke.yml for the full rationale. @@ -375,15 +399,20 @@ jobs: with: python-version: '3.12' - - name: Cache GGUF model file + # Split restore + save so a transient restore-side failure does not + # kill the whole job. See the matching block in the tool-calling job + # above for the full rationale (actions/cache#1621). + - name: Restore GGUF model cache id: cache-gguf - uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + continue-on-error: true with: path: gguf-cache key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1 - name: Download GGUF if cache miss - if: steps.cache-gguf.outputs.cache-hit != 'true' + id: download-gguf + if: steps.cache-gguf.outputs.cache-hit != 'true' || steps.cache-gguf.outcome != 'success' env: HF_TOKEN: ${{ secrets.HF_TOKEN }} run: | @@ -392,6 +421,13 @@ jobs: HF_HUB_ENABLE_HF_TRANSFER=1 \ hf download "$GGUF_REPO" "$GGUF_FILE" --local-dir gguf-cache + - name: Save GGUF model cache + if: always() && steps.download-gguf.outcome == 'success' + uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + with: + path: gguf-cache + key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1 + - name: Pre-install Windows tweaks (npm 11 + Defender exclusions) shell: pwsh # See studio-windows-update-smoke.yml for the full rationale. @@ -771,15 +807,23 @@ jobs: with: python-version: '3.12' - - name: Cache HF_HOME for ${{ env.GGUF_REPO }} (model + mmproj) + # Split restore + save so a transient restore-side failure does not + # kill the whole job. See the matching block in the tool-calling job + # for the full rationale (actions/cache#1621). This is the block that + # actually broke in run 25713577488: "Cache hit for: " was + # logged, the step exited non-zero in ~0.3 s without extracting the + # 3.4 GiB archive, and steps 6-15 were skipped. + - name: Restore HF_HOME cache for ${{ env.GGUF_REPO }} (model + mmproj) id: cache-hf - uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + continue-on-error: true with: path: hf-cache key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-${{ env.MMPROJ_FILE }}-v1 - name: Prime HF_HOME with the GGUF + mmproj - if: steps.cache-hf.outputs.cache-hit != 'true' + id: prime-hf + if: steps.cache-hf.outputs.cache-hit != 'true' || steps.cache-hf.outcome != 'success' env: HF_TOKEN: ${{ secrets.HF_TOKEN }} run: | @@ -790,6 +834,13 @@ jobs: HF_HUB_ENABLE_HF_TRANSFER=1 \ hf download "$GGUF_REPO" "$MMPROJ_FILE" + - name: Save HF_HOME cache for ${{ env.GGUF_REPO }} (model + mmproj) + if: always() && steps.prime-hf.outcome == 'success' + uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + with: + path: hf-cache + key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-${{ env.MMPROJ_FILE }}-v1 + - name: Pre-install Windows tweaks (npm 11 + Defender exclusions) shell: pwsh # See studio-windows-update-smoke.yml for the full rationale.