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, 23:15 UTC
[Doc][Typo] Fixing Missing Comma (#5403)
Roger Wang committed
Jun 11, 2024 at 00:20 UTC
3c4cebf751a6d2ff9ada2f8234bab17ba7283e09
1 file changed
+1
-1
docs/source/conf.py
+1
-1
@@ -92,7 +92,7 @@ autodoc_mock_imports = [
92
"vllm._C",
93
"PIL",
94
"numpy",
95
- 'triton'
95
+ 'triton',
96
"tqdm",
97
"tensorizer",
98
]