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, 03:00 UTC
[Doc] Fix vLLMEngine Doc Page (#3791)
Roger Wang committed
Apr 2, 2024 at 09:49 UTC
3bec41f41a28c0d51111b49e0db712009cf0439f
2 files changed
+4
-1
docs/requirements-docs.txt
+3
-1
@@ -7,4 +7,6 @@ sphinx-argparse
7
# packages to install to build the documentation
8
pydantic
9
-f https://download.pytorch.org/whl/cpu
10
-torch
\ No newline at end of file
10
+torch
11
+py-cpuinfo
12
+transformers
docs/source/conf.py
+1
@@ -75,6 +75,7 @@ html_theme_options = {
75
76
# Mock out external dependencies here.
77
autodoc_mock_imports = [
78
+ "cpuinfo",
79
"torch",
80
"transformers",
81
"psutil",