[Kernel][MoE] optimize moe_align_block_size (#29642)

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jinzhen Lin
2025-12-07 01:58:47 -08:00
committed by GitHub
co-authored by Jee Jee Li
parent 1b0482b9d1
commit 879ddb09c3
10 changed files with 195 additions and 63 deletions
+2
View File
@@ -1877,6 +1877,7 @@ def moe_align_block_size(
sorted_token_ids: torch.Tensor,
experts_ids: torch.Tensor,
num_tokens_post_pad: torch.Tensor,
expert_map: torch.Tensor | None = None,
) -> None:
torch.ops._moe_C.moe_align_block_size(
topk_ids,
@@ -1885,6 +1886,7 @@ def moe_align_block_size(
sorted_token_ids,
experts_ids,
num_tokens_post_pad,
expert_map,
)