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
[Doc] Mock new dependencies for documentation (#7245)
Roger Wang committed
Aug 6, 2024 at 23:43 UTC
2385c8f374dd2c9f1a42fdbb05eebfa78137474c
1 file changed
+2
docs/source/conf.py
+2
@@ -112,6 +112,8 @@ autodoc_mock_imports = [
112
"tensorizer",
113
"pynvml",
114
"outlines",
115
+ "gguf",
116
+ "lark",
117
]
118
119
for mock_target in autodoc_mock_imports: