nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[kernel] VSA kernel: one sm_100a / sm_103a image per listed arch; un-gate backward on sm_103a (#1833)

Browse Source 
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
lpc0220
2026-09-12 16:49:36 -07:00
committed by GitHub
co-authored by Claude Fable 5.1
parent a943220c11
commit aef4e9b3b1
7 changed files with 48 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/publish-kernel.yml
+2 -2
View File
@@ -176,11 +176,11 @@ jobs:
# the main extension for the full arch list. CMAKE_BUILD_PARALLEL_LEVEL caps
# Ninja so heavy CUTLASS/TK template TUs don't OOM the 16 GB runner (exit 143).
if [ "${{ matrix.platform.arch }}" = "aarch64" ]; then
export TORCH_CUDA_ARCH_LIST="10.0a;12.0a"
export TORCH_CUDA_ARCH_LIST="10.0a;10.3a;12.0a"
export CMAKE_ARGS="${CMAKE_ARGS:-} -DFASTVIDEO_KERNEL_BUILD_TK=OFF -DFASTVIDEO_KERNEL_BUILD_ATTN_QAT_INFER=ON"
export CMAKE_BUILD_PARALLEL_LEVEL=1
elif [ "${{ matrix.torch-cuda.torch-cuda-short }}" = "cu130" ]; then
export TORCH_CUDA_ARCH_LIST="9.0a;10.0a;12.0a"
export TORCH_CUDA_ARCH_LIST="9.0a;10.0a;10.3a;12.0a"
export CMAKE_ARGS="${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