Jiawei Xiang a640a89e25 [AMD][Radeon] Add the Support of RDNA3/RDNA3.5(gfx11) WMMA (#2044) ...

* feat: support RDNA3 wmma pattern

* fix: support tuple-based threadblock swizzle parsing in HIP codegen

* fix: improve some notes

* fix: support leading stage dims in WMMA shared loads

* fix: add transpose-aware RDNA WMMA A layout selection

* fix: fix annotation errors

* fix: use ffi helper for rdna generation detection

* fix: fix format error

* fix: fix lower call

2026-04-22 17:41:15 +08:00

..

example_amd_flash_attn_bwd.py

[AMD][Radeon] Add the Support of RDNA3/RDNA3.5(gfx11) WMMA (#2044)

2026-04-22 17:41:15 +08:00

example_amd_flash_attn_fwd.py

[AMD][Radeon] Upgrade Rocm version to be 7.2 and add the support of RDNA4 GPU (#1951)

2026-03-23 13:31:05 +08:00