Bartłomiej Kocot dbdf79d541 Add Clamp/Relu bf16/fp16 cast fixes (#2279) ...

* Add Clamp/Relu bf16/fp16 fixes

* fix

[ROCm/composable_kernel commit: 6e5acee0f9]

2025-06-03 18:31:46 +02:00

..

block

Add the instances for small sized GEMM in preshuffle and improve CMake Flag (#2212)

2025-05-20 15:05:08 -07:00

device

Fix grid size calc for bwd wei (#2226)

2025-05-26 16:51:09 +02:00

element

Add Clamp/Relu bf16/fp16 cast fixes (#2279)

2025-06-03 18:31:46 +02:00

grid

Use new mfma instructions for FP8 on gfx950 (#2202)

2025-05-19 17:29:51 -07:00

thread

Moe gemm activation (#2026)

2025-04-23 10:35:34 +08:00

warp

Use new mfma instructions for FP8 on gfx950 (#2202)

2025-05-19 17:29:51 -07:00