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, 05:30 UTC
[Docs] Improve docs navigation (#22720)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Aug 12, 2025 at 12:25 UTC
767e63b860dcb8952779f6035d2b215b53dd744d
7 files changed
+40
-19
.gitignore
+2
-1
@@ -150,7 +150,8 @@ venv.bak/
150
# mkdocs documentation
151
/site
152
docs/argparse
153
-docs/examples
153
+docs/examples/*
154
+!docs/examples/README.md
155
156
# mypy
157
.mypy_cache/
docs/.nav.yml
+7
-15
@@ -1,25 +1,17 @@
1
nav:
2
- - Home:
3
- - vLLM: README.md
2
+ - Home: README.md
3
+ - User Guide:
4
+ - usage/README.md
5
- Getting Started:
6
- getting_started/quickstart.md
7
- getting_started/installation
8
- Examples:
9
+ - examples/README.md
10
- Offline Inference: examples/offline_inference
11
- Online Serving: examples/online_serving
12
- Others: examples/others
11
- - Quick Links:
12
- - User Guide: usage/README.md
13
- - Developer Guide: contributing/README.md
14
- - API Reference: api/README.md
15
- - CLI Reference: cli/README.md
16
- - Timeline:
17
- - Roadmap: https://roadmap.vllm.ai
18
- - Releases: https://github.com/vllm-project/vllm/releases
19
- - User Guide:
20
- - Summary: usage/README.md
21
- - usage/v1_guide.md
13
- General:
14
+ - usage/v1_guide.md
15
- usage/*
16
- Inference and Serving:
17
- serving/offline_inference.md
@@ -32,7 +24,7 @@ nav:
24
- deployment/integrations
25
- Training: training
26
- Configuration:
35
- - Summary: configuration/README.md
27
+ - configuration/README.md
28
- configuration/*
29
- Models:
30
- models/supported_models.md
@@ -45,7 +37,7 @@ nav:
37
- features/*
38
- features/quantization
39
- Developer Guide:
48
- - Summary: contributing/README.md
40
+ - contributing/README.md
41
- General:
42
- glob: contributing/*
43
flatten_single_child_sections: true
docs/README.md
+11
@@ -21,6 +21,17 @@ vLLM is a fast and easy-to-use library for LLM inference and serving.
21
22
Originally developed in the [Sky Computing Lab](https://sky.cs.berkeley.edu) at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
23
24
+Where to get started with vLLM depends on the type of user. If you are looking to:
25
+
26
+- Run open-source models on vLLM, we recommend starting with the [Quickstart Guide](./getting_started/quickstart.md)
27
+- Build applications with vLLM, we recommend starting with the [User Guide](./usage)
28
+- Build vLLM, we recommend starting with [Developer Guide](./contributing)
29
+
30
+For information about the development of vLLM, see:
31
+
32
+- [Roadmap](https://roadmap.vllm.ai)
33
+- [Releases](https://github.com/vllm-project/vllm/releases)
34
+
35
vLLM is fast with:
36
37
- State-of-the-art serving throughput
docs/examples/README.md
new
+7
@@ -0,0 +1,7 @@
1
+# Examples
2
+
3
+vLLM's examples are split into three categories:
4
+
5
+- If you are using vLLM from within Python code, see [Offline Inference](./offline_inference/)
6
+- If you are using vLLM from an HTTP application or client, see [Online Serving](./online_serving/)
7
+- For examples of using some of vLLM's advanced features (e.g. LMCache or Tensorizer) which are not specific to either of the above use cases, see [Others](./others/)
docs/mkdocs/stylesheets/extra.css
+7
@@ -23,6 +23,13 @@ a:not(:has(svg)):not(.md-icon):not(.autorefs-external) {
23
}
24
}
25
26
+a[href*="localhost"]::after,
27
+a[href*="127.0.0.1"]::after,
28
+a[href*="org.readthedocs.build"]::after,
29
+a[href*="docs.vllm.ai"]::after {
30
+ display: none !important;
31
+}
32
+
33
/* Light mode: darker section titles */
34
body[data-md-color-scheme="default"] .md-nav__item--section > label.md-nav__link .md-ellipsis {
35
color: rgba(0, 0, 0, 0.7) !important;
docs/usage/README.md
+3
-1
@@ -1,6 +1,8 @@
1
# Using vLLM
2
3
-vLLM supports the following usage patterns:
3
+First, vLLM must be [installed](../getting_started/installation) for your chosen device in either a Python or Docker environment.
4
+
5
+Then, vLLM supports the following usage patterns:
6
7
- [Inference and Serving](../serving/offline_inference.md): Run a single instance of a model.
8
- [Deployment](../deployment/docker.md): Scale up model instances for production.
mkdocs.yaml
+3
-2
@@ -34,13 +34,14 @@ theme:
34
- content.action.edit
35
- content.code.copy
36
- content.tabs.link
37
+ - navigation.instant
38
+ - navigation.instant.progress
39
- navigation.tracking
40
- navigation.tabs
41
- navigation.tabs.sticky
42
- navigation.sections
41
- - navigation.prune
42
- - navigation.top
43
- navigation.indexes
44
+ - navigation.top
45
- search.highlight
46
- search.share
47
- toc.follow