Point Ling-3.0-flash-VL cookbook install section at the model image (#38539)
This commit is contained in:
@@ -22,14 +22,23 @@ pip install uv
|
||||
uv pip install --prerelease=allow sglang
|
||||
```
|
||||
|
||||
Then run the **Python** output of the command panel below in that environment.
|
||||
Then run the **Python** output of the command panel below in that environment. Ling-3.0-flash-VL support requires sglang with sgl-project/sglang#38526 (or newer); until it merges, install directly from the PR head:
|
||||
|
||||
```bash Command
|
||||
pip install --upgrade pip
|
||||
pip install uv
|
||||
uv pip install "sglang @ git+https://github.com/sgl-project/sglang.git@refs/pull/38526/head#subdirectory=python"
|
||||
uv pip install torchcodec==0.16.0 # optional, preferred video-decode backend
|
||||
```
|
||||
|
||||
Video input needs `decord` or `torchcodec` in the environment; audio is not supported. Downloading the checkpoint requires `HF_TOKEN`.
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Docker">
|
||||
|
||||
```bash Command
|
||||
docker pull lmsysorg/sglang:dev
|
||||
docker pull lmsysorg/sglang:dev-Ling-3.0-flash-VL
|
||||
```
|
||||
|
||||
For how to launch the image, see [Install → Method 3: Using Docker](../../../docs/get-started/install#method-3-using-docker). Substitute the inner `sglang serve ...` with what the command generator below produces.
|
||||
|
||||
Reference in New Issue
Block a user