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 16, 19:30 UTC
[Docs] Add RunLLM chat widget (#6857)
Chenggang Wu committed
Jul 27, 2024 at 09:24 UTC
f954d0715c8b68e780aac4a4f3ffd1ab56bebfcd
2 files changed
+18
docs/source/_static/custom.js
new
+16
@@ -0,0 +1,16 @@
1
+document.addEventListener("DOMContentLoaded", function () {
2
+ var script = document.createElement("script");
3
+ script.type = "module";
4
+ script.id = "runllm-widget-script"
5
+
6
+ script.src = "https://widget.runllm.com";
7
+
8
+ script.setAttribute("version", "stable");
9
+ script.setAttribute("runllm-keyboard-shortcut", "Mod+j"); // cmd-j or ctrl-j to open the widget.
10
+ script.setAttribute("runllm-name", "vLLM");
11
+ script.setAttribute("runllm-position", "BOTTOM_RIGHT");
12
+ script.setAttribute("runllm-assistant-id", "207");
13
+
14
+ script.async = true;
15
+ document.head.appendChild(script);
16
+ });
\ No newline at end of file
docs/source/conf.py
+2
@@ -68,6 +68,8 @@ html_theme_options = {
68
'use_repository_button': True,
69
'use_edit_page_button': True,
70
}
71
+html_static_path = ["_static"]
72
+html_js_files = ["custom.js"]
73
74
# see https://docs.readthedocs.io/en/stable/reference/environment-variables.html # noqa
75
READTHEDOCS_VERSION_TYPE = os.environ.get('READTHEDOCS_VERSION_TYPE')