Revert "fix some typos" (#6244)
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user