[CUDA] MatMulBlockQuantizedFp8Weight: fold the W8A8 activation QDQ into the decode GEMV - #31481
Open
tianleiwu wants to merge 2 commits into
Open
[CUDA] MatMulBlockQuantizedFp8Weight: fold the W8A8 activation QDQ into the decode GEMV#31481tianleiwu wants to merge 2 commits into
tianleiwu wants to merge 2 commits into
Azure Pipelines / Linux Android Emulator QNN CI Pipeline
succeeded
Aug 2, 2026 in 13m 33s
Build #20260802.5 succeeded
Loading