Aviral Goel 6fd8f800d8 fix(grouped_gemm): pipeline selection when tail_num varies per group and leads to numerical error (#2863) ...

* fix(grouped_gemm): numerical errors on gfx950 by correctly calculating the tail num

* WIP: add temp config to stress test numerical error correction

* refactor: remove comments

[ROCm/composable_kernel commit: db79fad16f]

2025-09-16 18:43:19 -07:00

..

ck

Added wmma support for gemm quantization: (#2841)

2025-09-16 16:23:29 -07:00

ck_tile

fix(grouped_gemm): pipeline selection when tail_num varies per group and leads to numerical error (#2863)

2025-09-16 18:43:19 -07:00

rapidjson

Add json dump support to output details from CK/CKTile Examples. (#2551)

2025-09-02 23:31:29 -07:00