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, 18:15 UTC
[Misc] fix typo in triton import warning (#7794)
Siyuan Liu committed
Aug 22, 2024 at 13:51 UTC
a15224642832acdddd757ddc95ed40a0ad1be33d
1 file changed
+1
-1
vllm/triton_utils/importing.py
+1
-1
@@ -8,4 +8,4 @@ HAS_TRITON = find_spec("triton") is not None
8
9
if not HAS_TRITON:
10
logger.info("Triton not installed; certain GPU-related functions"
11
- " will be not be available.")
11
+ " will not be available.")