2026-02-06 16:13:50 +08:00
|
|
|
# Changelog
|
|
|
|
|
|
|
|
|
|
All notable changes to aha will be documented in this file.
|
|
|
|
|
|
|
|
|
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
|
|
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
|
|
|
|
2026-04-15 17:42:41 +08:00
|
|
|
### 2026-04-15
|
|
|
|
|
- add FireRedVAD
|
|
|
|
|
|
2026-04-10 23:06:09 +08:00
|
|
|
### 2026-04-10
|
|
|
|
|
- fix LiquidAI/LFM2.5-VL-450M chat_template load bug
|
|
|
|
|
|
2026-04-08 18:55:03 +08:00
|
|
|
### 2026-04-08
|
|
|
|
|
- add VoxCPM2
|
|
|
|
|
|
2026-04-06 19:32:25 +08:00
|
|
|
### 0.2.5 (2026-04-06)
|
|
|
|
|
- add qwen3-embedding/qwen3-reranker/all-minilm-l6-v2
|
|
|
|
|
|
2026-04-03 14:15:10 +08:00
|
|
|
### 2026-04-03
|
2026-04-03 20:43:51 +08:00
|
|
|
- CLI update: subcommand must be specified
|
2026-04-03 14:15:10 +08:00
|
|
|
- ChatCompletionParameters add repeat_penalty and repeat_last_n
|
2026-04-03 20:43:51 +08:00
|
|
|
- generate add penalty repeat
|
2026-04-03 14:15:10 +08:00
|
|
|
|
2026-04-02 22:22:52 +08:00
|
|
|
### 2026-04-02
|
|
|
|
|
- refactor generate code
|
|
|
|
|
- \<think\>...\</think\> The content of the thought chain is returned using the reasoning_content field.
|
|
|
|
|
- response add time info
|
|
|
|
|
|
2026-04-01 19:11:10 +08:00
|
|
|
### 2026-04-01
|
|
|
|
|
- refactor deepseek_ocr/fun_asr_nano generate code
|
|
|
|
|
|
2026-03-31 12:30:12 +08:00
|
|
|
### 2026-03-31
|
2026-04-03 14:15:10 +08:00
|
|
|
- add server and cli mod
|
2026-03-31 18:45:01 +08:00
|
|
|
- aha model name use modelscope id replace
|
|
|
|
|
- update WhichModel enum
|
|
|
|
|
- Usage add time info
|
2026-03-31 12:30:12 +08:00
|
|
|
- dependencies delete aha_openai_dive,chrono
|
|
|
|
|
|
2026-04-06 19:34:05 +08:00
|
|
|
### 2026-03-30
|
2026-03-30 12:51:45 +08:00
|
|
|
- add LFM2.5VL-1.6B
|
|
|
|
|
- add LFM2VL-1.6B
|
|
|
|
|
|
2026-03-23 22:07:41 +08:00
|
|
|
### v0.2.4 (2026-03-23)
|
|
|
|
|
- add LFM2.5-1.2B-Instruct
|
|
|
|
|
- add LFM2-1.2B
|
|
|
|
|
|
2026-03-19 17:24:08 +08:00
|
|
|
### v0.2.3 (2026-03-18)
|
2026-03-18 19:15:21 +08:00
|
|
|
- add DeepSeek-OCR-2
|
|
|
|
|
|
2026-03-17 15:39:34 +08:00
|
|
|
### 2026-03-17
|
2026-03-17 21:35:54 +08:00
|
|
|
- add PaddleOCR-VL1.5 model
|
2026-03-17 15:39:34 +08:00
|
|
|
- fix qwen3.5 position_ids create bug
|
|
|
|
|
- cli param add
|
|
|
|
|
- gguf_path: Local GGUF model weight path (required for loading models with GGUF)
|
|
|
|
|
- mmproj_path: Local path to mmproj GGUF weights (required for multimodal model GGUF loading)
|
|
|
|
|
- WhichModel add qwen3.5-gguf
|
|
|
|
|
|
2026-03-16 14:50:59 +08:00
|
|
|
### 2026-03-16
|
|
|
|
|
- Added Qwen3.5 mmproj
|
|
|
|
|
|
2026-03-14 20:23:07 +08:00
|
|
|
### 2026-03-14
|
|
|
|
|
- update rust version
|
|
|
|
|
- Added Qwen3.5 gguf support, but the 4B model still has issues; to be resolved.
|
|
|
|
|
|
2026-03-07 18:08:06 +08:00
|
|
|
## [0.2.2] (2026-03-07)
|
|
|
|
|
- Added GLM-OCR model
|
|
|
|
|
|
2026-03-05 21:57:03 +08:00
|
|
|
## [0.2.1] - (2026-03-05)
|
|
|
|
|
- Added Qwen3.5 model
|
|
|
|
|
|
|
|
|
|
### 2026-03-01
|
|
|
|
|
- update interpolate.rs
|
|
|
|
|
|
|
|
|
|
### 2026-02-24
|
|
|
|
|
- update candle version 0.9.2
|
|
|
|
|
|
2026-02-06 16:13:50 +08:00
|
|
|
## [0.2.0] - 2026-02-05
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- Qwen3-ASR speech recognition model
|
|
|
|
|
|
|
|
|
|
## [0.1.9] - 2026-01-31
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- CLI `list` subcommand to show supported models
|
|
|
|
|
- CLI subcommand structure support (`cli`, `serv`, `download`, `run`)
|
|
|
|
|
- Direct model inference via new `run` subcommand
|
|
|
|
|
|
|
|
|
|
### Fixed
|
|
|
|
|
- Qwen3VL thinking startswith bug
|
|
|
|
|
- `aha run` multiple inputs bug
|
|
|
|
|
|
|
|
|
|
## [0.1.8] - 2026-01-17
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- Qwen3 text model support
|
|
|
|
|
- Fun-ASR-Nano-2512 speech recognition model
|
|
|
|
|
|
|
|
|
|
### Fixed
|
|
|
|
|
- ModelScope Fun-ASR-Nano model load error
|
|
|
|
|
|
|
|
|
|
### Changed
|
|
|
|
|
- Updated audio resampling with rubato
|
|
|
|
|
|
|
|
|
|
## [0.1.7] - 2026-01-07
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- GLM-ASR-Nano-2512 speech recognition model
|
|
|
|
|
- Metal (GPU) support for Apple Silicon
|
|
|
|
|
- Dynamic home directory and model download script
|
|
|
|
|
|
|
|
|
|
## [0.1.6] - 2025-12-23
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- RMBG-2.0 background removal model
|
|
|
|
|
- Image and audio API endpoints
|
|
|
|
|
|
|
|
|
|
### Changed
|
|
|
|
|
- Performance optimizations for RMBG2.0 image processing
|
|
|
|
|
|
|
|
|
|
## [0.1.5] - 2025-12-11
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- VoxCPM1.5 voice generation model
|
|
|
|
|
- PaddleOCR-VL text recognition model
|
|
|
|
|
|
|
|
|
|
## [0.1.4] - 2025-12-09
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- PaddleOCR-VL model support
|
|
|
|
|
- FFmpeg feature for multimedia processing
|
|
|
|
|
|
|
|
|
|
## [0.1.3] - 2025-12-03
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- Hunyuan-OCR model support
|
|
|
|
|
|
|
|
|
|
## [0.1.2] - 2025-11-23
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- DeepSeek-OCR model support
|
|
|
|
|
|
|
|
|
|
## [0.1.1] - 2025-11-12
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- Qwen3-VL models (2B, 4B, 8B, 32B)
|
|
|
|
|
|
|
|
|
|
### Fixed
|
|
|
|
|
- Added serde default for tie_word_embeddings in Qwen3VL
|
|
|
|
|
|
|
|
|
|
## [0.1.0] - 2025-10-10
|
|
|
|
|
|
|
|
|
|
### Added
|
|
|
|
|
- Initial release
|
|
|
|
|
- Qwen2.5-VL model support
|
|
|
|
|
- MiniCPM4 model support
|
|
|
|
|
- VoxCPM voice generation model
|
|
|
|
|
- OpenAI-compatible REST API
|
|
|
|
|
- CLI interface for all model types
|
