[ci] cap kernel wheel build parallelism to avoid runner OOM (#1483)

Author: SolitaryThinker

.github/workflows/publish-kernel.yml

@@ -148,12 +148,22 @@ jobs:
           # The CUDA 13 (cu130) leg additionally targets Blackwell sm_120a and builds the
           # attn_qat_infer FP4 inference kernels (they need CUDA Toolkit 12.8+, so the cu126 leg
           # stays Hopper-only and ships without them).
+          # Cap Ninja build concurrency to fit the 16 GB standard runner. CUTLASS FP4
+          # and ThunderKittens template TUs each need several GB; Ninja's default
+          # (cores+2 ≈ 6 parallel jobs) exhausts RAM and the host OOM-kills the build
+          # (SIGTERM / exit 143, surfaced as "runner lost communication").
           if [ "${{ matrix.torch-cuda.torch-cuda-short }}" = "cu130" ]; then
             export TORCH_CUDA_ARCH_LIST="9.0a;12.0a"
             export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DFASTVIDEO_KERNEL_BUILD_ATTN_QAT_INFER=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
+            # A single FP4 TU (attn_qat_infer) can use ~8-12 GB on its own, so serialize.
+            export CMAKE_BUILD_PARALLEL_LEVEL=1
           else
             export TORCH_CUDA_ARCH_LIST="9.0a"
             export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=ON -DCMAKE_CUDA_ARCHITECTURES=90a"
+            # No FP4 here; only the two TK TUs are heavy (single-arch) and they fit
+            # side by side. Uncapped (cores+2=6) has built but occasionally OOMs when
+            # the light TUs pile on; -j4 overlaps them safely (~12-14 GB peak).
+            export CMAKE_BUILD_PARALLEL_LEVEL=4
           fi
 
           # Build standard wheel (no local version suffix) for PyPI