[gfx1201] Add tuned kernel configs and FP8 attention support for AMD RDNA4 (Radeon AI PRO R9700)#2242

Draft

vllmellm wants to merge 9 commits intoROCm:mainfrom

EmbeddedLLM:rdna4-ck

Commits on Feb 26, 2026

add tuned ck config for a8w8 blockscale gemm
big-yellow-duck
committed

Commits on Feb 27, 2026

Commits on Mar 2, 2026

Commits on Mar 4, 2026

add tuned triton configs
big-yellow-duck
committed

Commits on Mar 5, 2026

added a8w8_blockscale_configs for qwen3-30b-a3b-fp8 for gfx1201
big-yellow-duck
committed

Commits on Mar 10, 2026

organize tuned configs
big-yellow-duck
committed

Commits on Mar 12, 2026

sort out a8w8_blockscale_tuned config
big-yellow-duck
committed