Bump the version to 0.3.0. (#1014)

* Bump the version to 0.3.0.

* Changelog update.
This commit is contained in:
Laurent Mazare
2023-10-01 13:51:57 +01:00
committed by GitHub
parent f6054e9d60
commit 096dee7073
20 changed files with 71 additions and 65 deletions

View File

@ -1,12 +1,38 @@
# Changelog
This documents the main changes to the `candle` crate.
## v0.2.3 - Unreleased
## v0.3.1 - Unreleased
### Added
### Modified
## v0.3.0 - 2023-10-01
### Added
- Added the Mistral 7b v0.1 model
[983](https://github.com/huggingface/candle/pull/983).
- Quantized version of the Mistral model
[1009](https://github.com/huggingface/candle/pull/1009).
- Add the gelu-erf op and activation function
[969](https://github.com/huggingface/candle/pull/969).
- Add the mixformer/phi-v1.5 model
[930](https://github.com/huggingface/candle/pull/930).
- Add the sclice-scatter op
[927](https://github.com/huggingface/candle/pull/927).
- Add the Wuerstchen diffusion model
[911](https://github.com/huggingface/candle/pull/911).
### Modified
- Support for simd128 intrinsics in some quantized vecdots
[982](https://github.com/huggingface/candle/pull/982).
- Optimize the index-select cuda kernel
[976](https://github.com/huggingface/candle/pull/976).
- Self-contained safetensor wrappers
[946](https://github.com/huggingface/candle/pull/946).
## v0.2.2 - 2023-09-18
### Added