[Kernel] DeepGemm MoE : Integrate triton permute / unpermute kernels (#20903)

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
This commit is contained in:
Varun Sundar Rabindranath
2025-07-17 08:10:37 +00:00
committed by GitHub
co-authored by Varun Sundar Rabindranath
parent fdc5b43d20
commit 11dfdf21bf
10 changed files with 490 additions and 58 deletions
@@ -85,7 +85,6 @@ def make_config_arg_parser(description: str):
help="num topk")
parser.add_argument(
"--fused-moe-chunk-size",
nargs="+",
type=int,
help="Fused moe chunk size used for the non-batched fused experts impl."
)