@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 3bec41f41a
Fork 0

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",