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 15, 08:30 UTC
[Doc] Use a different color for the announcement (#18616)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 23, 2025 at 23:25 UTC
022d8abe29531d0023ea022a64af230719df93ca
2 files changed
+7
docs/mkdocs/stylesheets/extra.css
new
+4
@@ -0,0 +1,4 @@
1
+.md-banner {
2
+ background-color: var(--md-warning-bg-color);
3
+ color: var(--md-warning-fg-color);
4
+}
mkdocs.yaml
+3
@@ -113,6 +113,9 @@ markdown_extensions:
113
- mdx_math:
114
enable_dollar_delimiter: true
115
116
+extra_css:
117
+ - mkdocs/stylesheets/extra.css
118
+
119
extra_javascript:
120
- mkdocs/javascript/run_llm_widget.js
121
- https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML