Temporary disable persistent topk (#41442)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
2026-04-30 20:37:19 -07:00
parent 88d34c6409
commit 05ebca5250
1 changed files with 1 additions and 1 deletions
@@ -320,7 +320,7 @@ def sparse_attn_indexer(
        num_rows = logits.shape[0]
        topk_indices = topk_indices_buffer[:num_padded_tokens, :topk_tokens]

-        if current_platform.is_cuda() and topk_tokens in (512, 1024, 2048):
+        if current_platform.is_cuda() and topk_tokens in (512, 2048):
            workspace_manager = current_workspace_manager()
            (topk_workspace,) = workspace_manager.get_simultaneous(
                ((RADIX_TOPK_WORKSPACE_SIZE,), torch.uint8),