A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 19:30 UTC
[Misc] Fix typo in GroupCoordinator.recv() (#7167)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Rui Qiao committed
Aug 5, 2024 at 11:10 UTC
997cf78308d292b03c8a1e68d8d1a1f599551937
1 file changed
+2
-2
vllm/distributed/parallel_state.py
+2
-2
@@ -713,8 +713,8 @@ class GroupCoordinator:
713
size: torch.Size,
714
dtype: torch.dtype,
715
src: Optional[int] = None) -> torch.Tensor:
716
- """Receives a tensor from the src rank."""
717
- """NOTE: `src` is the local rank of the destination rank."""
716
+ """Receives a tensor from the source rank."""
717
+ """NOTE: `src` is the local rank of the source rank."""
718
if src is None:
719
src = (self.rank_in_group - 1) % self.world_size
720