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, 22:00 UTC
[Doc] Fix Mock Import (#6094)
Roger Wang committed
Jul 3, 2024 at 00:13 UTC
f1c78138aa28e58eeaafa4791788fe6ceddf1dd8
1 file changed
+1
docs/source/conf.py
+1
@@ -96,6 +96,7 @@ autodoc_mock_imports = [
96
'triton',
97
"tqdm",
98
"tensorizer",
99
+ "pynvml",
100
]
101
102
for mock_target in autodoc_mock_imports: