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, 04:15 UTC
[Docs] Fix Unmocked Imports (#3275)
Roger Wang committed
Mar 8, 2024 at 09:58 UTC
99c3cfb83c20d45899ab8cbfdddce98c7cffb7b1
1 file changed
+9
-2
docs/source/conf.py
+9
-2
@@ -72,8 +72,15 @@ html_theme_options = {
72
73
# Mock out external dependencies here.
74
autodoc_mock_imports = [
75
- "torch", "transformers", "psutil", "prometheus_client", "sentencepiece",
76
- "vllm.cuda_utils", "vllm._C"
75
+ "torch",
76
+ "transformers",
77
+ "psutil",
78
+ "prometheus_client",
79
+ "sentencepiece",
80
+ "vllm.cuda_utils",
81
+ "vllm._C",
82
+ "numpy",
83
+ "tqdm",
84
]
85
86
for mock_target in autodoc_mock_imports: