2023-08-23 19:58:55 +08:00
|
|
|
# Changelog
|
|
|
|
This documents the main changes to the `candle` crate.
|
|
|
|
|
|
|
|
## Unreleased
|
|
|
|
### Added
|
2023-08-26 20:00:24 +08:00
|
|
|
- Support more quantized types, e.g. Q2K, Q4K, Q5K...
|
|
|
|
[586](https://github.com/huggingface/candle/pull/586).
|
2023-08-26 01:01:38 +08:00
|
|
|
- Add pose estimation to the yolo example
|
|
|
|
[589](https://github.com/huggingface/candle/pull/589).
|
|
|
|
- Api to write GGUF files
|
|
|
|
[585](https://github.com/huggingface/candle/pull/585).
|
|
|
|
- Support more quantization types
|
|
|
|
[580](https://github.com/huggingface/candle/pull/580).
|
|
|
|
- Add EfficientNet as an example Computer Vision model
|
|
|
|
[572](https://github.com/huggingface/candle/pull/572).
|
2023-08-23 19:58:55 +08:00
|
|
|
- Add a group parameter to convolutions
|
|
|
|
[566](https://github.com/huggingface/candle/pull/566).
|
|
|
|
- New dtype: int64
|
|
|
|
[563](https://github.com/huggingface/candle/pull/563).
|
|
|
|
- Handling of the GGUF file format.
|
|
|
|
[559](https://github.com/huggingface/candle/pull/559).
|
|
|
|
|
|
|
|
## v0.1.2 - 2023-08-21
|