anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Update gradio docs (#95)

Browse Source 
Signed-off-by: samithuang <285365963@qq.com>
This commit is contained in:
Samit authored and GitHub committed 2025-11-28 15:06:33 +08:00
1 parent 54351f2ac8
commit befc7fdfd7
1 file changed
+8 -12
Download Patch File Download Diff File Expand all files Collapse all files
examples/online_serving/README.md
+8 -12
View File
@@ -56,22 +56,18 @@ Then open `http://localhost:7861/` on your local browser to interact with the we
### Options ### Options
The gradio demo also supports running with an existing API server and can be customized with the following arguments. You can customize its basic launch parameters:
```bash ```bash
python gradio_demo.py \ python gradio_demo.py \
--model Qwen/Qwen2.5-Omni-7B \ --model Qwen/Qwen2.5-Omni-7B \
--use-api-server \
--api-base http://localhost:8091/v1 \
--ip 127.0.0.1 \ --ip 127.0.0.1 \
--port 7861 --port 7861 \
--stage-configs-path /path/to/stage_configs.yaml
``` ```
- `--model`: Model name - `--model`: Local model checkpoint to load (default `Qwen/Qwen2.5-Omni-7B`).
- `--use-api-server`: If set, connect to an existing vLLM HTTP API server instead of running AsyncOmniLLM locally. - `--ip`: Host/IP for the Gradio server (default `127.0.0.1`).
- `--api-base`: Base URL for vllm serve (only used when `use-api-server` is set, default: http://localhost:8091/v1) - `--port`: Port for the Gradio server (default `7861`).
- `--ip`: Host/IP for Gradio server (default: 127.0.0.1) - `--stage-configs-path`: Optional path to custom stage configs YAML.
- `--port`: Port for Gradio server (default: 7861) - `--share`: Set to expose a temporary public link via Gradio.
- `--stage-configs-path`: Path to custom stage configs YAML file (optional)
- `--share`: Share the Gradio demo publicly (creates a public link)