2023-08-23 19:58:55 +08:00
|
|
|
# Changelog
|
|
|
|
|
This documents the main changes to the `candle` crate.
|
|
|
|
|
|
2023-10-01 20:51:57 +08:00
|
|
|
## v0.3.1 - Unreleased
|
2023-09-18 19:14:03 +08:00
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
|
|
|
|
|
### Modified
|
|
|
|
|
|
2023-10-01 20:51:57 +08:00
|
|
|
## 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).
|
|
|
|
|
|
2023-09-18 19:14:03 +08:00
|
|
|
## v0.2.2 - 2023-09-18
|
2023-08-30 16:27:56 +08:00
|
|
|
|
|
|
|
|
### Added
|
2023-09-13 00:10:16 +08:00
|
|
|
- Support for `top_p` sampling
|
|
|
|
|
[819](https://github.com/huggingface/candle/pull/819).
|
2023-09-18 19:14:03 +08:00
|
|
|
- T5 model including decoding
|
|
|
|
|
[864](https://github.com/huggingface/candle/pull/864).
|
|
|
|
|
- 1-d upsampling
|
|
|
|
|
[839](https://github.com/huggingface/candle/pull/839).
|
2023-08-30 16:27:56 +08:00
|
|
|
|
2023-09-12 13:39:24 +08:00
|
|
|
### Modified
|
2023-09-18 19:14:03 +08:00
|
|
|
- Bugfix for conv2d
|
|
|
|
|
[820](https://github.com/huggingface/candle/pull/820).
|
|
|
|
|
- Support tensor based indexing using `.i`
|
|
|
|
|
[842](https://github.com/huggingface/candle/pull/842).
|
2023-09-12 13:39:24 +08:00
|
|
|
|
|
|
|
|
## v0.2.1 - 2023-09-11
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- Add some RNNs (GRU and LSTM) in `candle-nn`
|
|
|
|
|
[674](https://github.com/huggingface/candle/pull/674),
|
|
|
|
|
[688](https://github.com/huggingface/candle/pull/688).
|
|
|
|
|
- gguf v2 support
|
|
|
|
|
[725](https://github.com/huggingface/candle/pull/725).
|
|
|
|
|
- Quantized llama example in Python using the pyo3 api
|
|
|
|
|
[716](https://github.com/huggingface/candle/pull/716).
|
|
|
|
|
- `candle-nn` layer for conv2d-transposed
|
|
|
|
|
[760](https://github.com/huggingface/candle/pull/760).
|
|
|
|
|
- Add the Segment-Anything Model (SAM) as an example
|
|
|
|
|
[773](https://github.com/huggingface/candle/pull/773).
|
|
|
|
|
- TinyViT backbone for the segemnt anything example
|
|
|
|
|
[787](https://github.com/huggingface/candle/pull/787).
|
|
|
|
|
- Shape with holes support
|
|
|
|
|
[770](https://github.com/huggingface/candle/pull/770).
|
|
|
|
|
|
2023-08-30 16:27:56 +08:00
|
|
|
### Modified
|
|
|
|
|
- Dilations are now supported in conv-transpose2d.
|
|
|
|
|
[671](https://github.com/huggingface/candle/pull/671).
|
2023-09-12 13:39:24 +08:00
|
|
|
- Interactive mode for the quantized model
|
|
|
|
|
[690](https://github.com/huggingface/candle/pull/690).
|
|
|
|
|
- Faster softmax operation
|
|
|
|
|
[747](https://github.com/huggingface/candle/pull/747).
|
|
|
|
|
- Faster convolution operations on CPU and CUDA via im2col
|
|
|
|
|
[802](https://github.com/huggingface/candle/pull/802).
|
|
|
|
|
- Moving some models to a more central location
|
|
|
|
|
[796](https://github.com/huggingface/candle/pull/796).
|
2023-08-30 16:27:56 +08:00
|
|
|
|
|
|
|
|
## v0.2.0 - 2023-08-30
|
|
|
|
|
|
2023-08-23 19:58:55 +08:00
|
|
|
### Added
|
2023-08-30 16:27:56 +08:00
|
|
|
- Add the powf op
|
|
|
|
|
[664](https://github.com/huggingface/candle/pull/664).
|
2023-08-29 19:55:56 +08:00
|
|
|
- Stable Diffusion XL support
|
|
|
|
|
[647](https://github.com/huggingface/candle/pull/647).
|
|
|
|
|
- Add the conv-transpose2d op
|
|
|
|
|
[635](https://github.com/huggingface/candle/pull/635).
|
2023-08-28 01:17:11 +08:00
|
|
|
- Refactor the VarBuilder api
|
|
|
|
|
[627](https://github.com/huggingface/candle/pull/627).
|
|
|
|
|
- Add some quantization command
|
|
|
|
|
[625](https://github.com/huggingface/candle/pull/625).
|
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
|
