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 14, 22:35 UTC
[Docs] Reduce the size of the built docs (#21920)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Jul 30, 2025 at 15:35 UTC
88edf5994c123314cc3b18621352dd118bec2b99
2 files changed
+8
mkdocs.yaml
+7
@@ -67,6 +67,13 @@ plugins:
67
exclude:
68
- argparse/*
69
- examples/*
70
+ - minify:
71
+ minify_html: true
72
+ minify_js: true
73
+ minify_css: true
74
+ cache_safe: true
75
+ js_files: [docs/mkdocs/javascript/*.js]
76
+ css_files: [docs/mkdocs/stylesheets/*.css]
77
# For API reference generation
78
- api-autonav:
79
modules: ["vllm"]
requirements/docs.txt
+1
@@ -6,6 +6,7 @@ mkdocs-gen-files
6
mkdocs-awesome-nav
7
mkdocs-glightbox
8
mkdocs-git-revision-date-localized-plugin
9
+mkdocs-minify-plugin
10
python-markdown-math
11
regex
12
ruff