[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Codex <codex@openai.com>
This commit is contained in:
Roberto L. Castro
2026-09-12 00:05:59 -04:00
committed by GitHub
co-authored by Codex
parent 485421b1c3
commit 120ec4ebd2
28 changed files with 3124 additions and 2551 deletions
+8
View File
@@ -22,6 +22,14 @@ _TORCH_TO_CUTE_DTYPE = {
torch.float32: Float32,
}
def torch_to_cute_dtype(dtype: torch.dtype):
try:
return _TORCH_TO_CUTE_DTYPE[dtype]
except KeyError as exc:
raise TypeError(f"Unsupported CuTe dtype {dtype}") from exc
_CUTE_TO_PTX_DTYPE = {
BFloat16: "bf16",
Float16: "f16",