support batch infer in vllm
Former-commit-id: 3ef5ed3b9a44eed2f7e3ff221dfc343d0a97c0b5
This commit is contained in:
@@ -594,7 +594,7 @@ API_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml
|
||||
> [!TIP]
|
||||
> API 文档请查阅[这里](https://platform.openai.com/docs/api-reference/chat/create)。
|
||||
>
|
||||
> 示例:[图像理解](scripts/test_image.py) | [工具调用](scripts/test_toolcall.py)
|
||||
> 示例:[图像理解](scripts/api_example/test_image.py) | [工具调用](scripts/api_example/test_toolcall.py)
|
||||
|
||||
### 从魔搭社区下载
|
||||
|
||||
|
||||
Reference in New Issue
Block a user