Brayden ZhongandBrayden Zhong b3ee679467 [MXFP8] Use FlashInfer CUTLASS for dense GEMM on SM120, delete Triton path (#33208) ...

Co-authored-by: Brayden Zhong <brayden@radixark.ai>

2026-08-07 14:30:43 -07:00

..

benchmark

perf(hisparse): eliminate redundant swap output fill (#32483)

2026-07-31 12:09:44 +08:00

ops

[MXFP8] Use FlashInfer CUTLASS for dense GEMM on SM120, delete Triton path (#33208)

2026-08-07 14:30:43 -07:00

test_dcp_lse_combine.py

[Fix] Honor FlashMLA natural-log LSE in DCP reduction (#33065)

2026-08-03 19:55:52 -07:00

test_fused_op_dispatch.py

[Kernel] Unify BaseFusedOp and MultiPlatformOp dispatch (#33205)

2026-08-06 08:52:09 +08:00

test_kernel_inventory.py

[Kernel] Add inventory guards and clean benchmark layout (#32788)

2026-07-30 09:03:24 +08:00