|
|
1a49aa3779
|
added auto-detection for the output type on the client side to be able to download binary files such as videos
|
2025-01-10 19:12:21 +01:00 |
|
|
|
775c78c6cb
|
added a lock to avoid two inference at the same time and added consequent support for asynchronous generator based model
|
2025-01-10 19:11:48 +01:00 |
|
|
|
c6d779f591
|
added support for tags to categorise the models
|
2025-01-10 11:08:10 +01:00 |
|
|
|
b89fafdc96
|
fix: uploaded file were closed automatically before the model could infer their data
|
2025-01-10 11:05:41 +01:00 |
|
|
|
639425ad7d
|
fixed model information being incorrect
|
2025-01-10 00:25:07 +01:00 |
|
|
|
7bd84c8570
|
added support of inputs parameters that are recognised by the API.
Models are now loaded in separate endpoints for the inputs to be easier to recognise
|
2025-01-09 23:12:54 +01:00 |
|
|
|
900c58ffcb
|
added accelerate to the base requirements of the project since it seem to only work when installed early and is essential in running models
|
2025-01-08 22:21:02 +01:00 |
|
|
|
dc8e42e94d
|
fixed the configuration name for "response_mimetype"
|
2025-01-08 21:54:27 +01:00 |
|
|
|
71eff944dd
|
mark the model as loaded once loaded
|
2025-01-08 20:35:14 +01:00 |
|
|
|
66ae63ac19
|
fixed the request field having the wrong name
|
2025-01-08 19:48:17 +01:00 |
|
|
|
e2ebbf8a82
|
base for the application : support custom python application and auto-install dependencies
|
2025-01-08 19:00:47 +01:00 |
|
|
|
a20371e1ab
|
Initial commit
|
2025-01-07 21:45:51 +01:00 |
|
