cjandcaojian5 2a06036faa [BugFix] Reject mixed packed x2 operand dtypes (#2802) ...

* Reject mixed packed x2 operand dtypes

* Cover mixed first fma2 operand

---------

Co-authored-by: caojian5 <caojian5@huawei.com>

2026-07-29 15:32:33 +08:00

..

test_cuda_bfloat16_math_intrinsics.py

[CUDA] Reduce template include overhead (#2474)

2026-07-01 16:53:07 +08:00

test_cuda_f32x2_intrinsics.py

[BugFix] Reject mixed packed x2 operand dtypes (#2802)

2026-07-29 15:32:33 +08:00

test_cuda_mma_sm75_dispatch.py

[TileOP] Add SM70 GEMM FMA fallback (#2339)

2026-07-27 20:30:42 +08:00

test_tilelang_cuda_tcgen05_operand_layout.py

[CUDA] Support arbitrary TMEM layouts (#2785)

2026-07-29 13:07:28 +08:00

test_tma_dsmem.py

[BugFix] Fallback non-16B cluster bulk copies (#2683)

2026-07-27 23:39:50 +08:00

test_tma_multicast_demo.py

[Transform] Materialize kernel launch per backend (#2387)

2026-06-12 17:14:02 +08:00