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 10, 07:45 UTC
[Doc] Add documentation for offline API docs feature (#32134)
Signed-off-by: rickychen-infinirc <ricky.chen@infinirc.com>
RickyChen / 陳昭儒 committed
Jan 12, 2026 at 18:33 UTC
a5f89ae296c5c25c996eb0bb567f0d70e7577aff
1 file changed
+8
docs/serving/openai_compatible_server.md
+8
@@ -173,6 +173,14 @@ with `--enable-request-id-headers`.
173
print(completion._request_id)
174
```
175
176
+## Offline API Documentation
177
+
178
+The FastAPI `/docs` endpoint requires an internet connection by default. To enable offline access in air-gapped environments, use the `--enable-offline-docs` flag:
179
+
180
+```bash
181
+vllm serve NousResearch/Meta-Llama-3-8B-Instruct --enable-offline-docs
182
+```
183
+
184
## API Reference
185
186
### Completions API