remove moe_align_block_size torch.zeros in small batch/expert mode (#5298)

2025-04-12 03:13:55 +08:00
parent a0a9f6d64f
commit 60bcbf2a35
1 changed files with 1 additions and 1 deletions
--- a/python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
+++ b/python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
@@ -707,7 +707,7 @@ def moe_align_block_size(
            dtype=torch.int32,
            device=topk_ids.device,
        )
-        cumsum_buffer = torch.zeros(
+        cumsum_buffer = torch.empty(
            num_experts + 1, dtype=torch.int32, device=topk_ids.device
        )