fix some typos (#6209)

Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-13 01:42:38 +08:00
parent 3ee40ff919
commit d738ab52f8
95 changed files with 276 additions and 276 deletions
@@ -874,7 +874,7 @@ def fast_mla_decode_plan(
 ) -> None:
    """A faster version of BatchMLAPagedAttentionWrapper::plan,
    for skipping the stream synchronization in original plan function during
-    cuda graph replaying.
+    CUDA graph replaying.
    """
    self._causal = causal
    self._page_size = page_size