@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 5f036d2bcc
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 17, 05:30 UTC

[Minor] Fix warning on Ray dependencies (#2630)

Woosuk Kwon committed Jan 27, 2024 at 15:43 UTC 5f036d2bcc5244ca431212167c94700e5ae7a8e0
1 file changed +1 -1
vllm/engine/ray_utils.py
+1 -1
@@ -43,7 +43,7 @@ try:
43 except ImportError as e:
44 logger.warning(f"Failed to import Ray with {e!r}. "
45 "For distributed inference, please install Ray with "
46 - "`pip install ray pandas pyarrow`.")
46 + "`pip install ray`.")
47 ray = None
48 RayWorkerVllm = None
49