@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 997cf78308
Fork 0

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