update doc

This commit is contained in:
jhqxxx
2026-03-30 12:51:45 +08:00
parent bb3b6aa834
commit db2d3a1eb4
5 changed files with 21 additions and 28 deletions
+1 -1
View File
@@ -4,7 +4,7 @@ version = "0.2.4"
edition = "2024" edition = "2024"
repository = "https://github.com/jhqxxx/aha" repository = "https://github.com/jhqxxx/aha"
license = "Apache-2.0" license = "Apache-2.0"
description = "aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR), MiniCPM4, VoxCPM/1.5, DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5, RMBG2.0, GLM(ASR-Nano-2512/OCR), Fun-ASR-Nano-2512, LFM(2/2.5)" description = "aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR), MiniCPM4, VoxCPM/1.5, DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5, RMBG2.0, GLM(ASR-Nano-2512/OCR), Fun-ASR-Nano-2512, LFM(2/2.5/2VL/2.5VL)"
[dependencies] [dependencies]
candle-core = { version = "0.9.2" } candle-core = { version = "0.9.2" }
+6 -13
View File
@@ -25,6 +25,10 @@
aha is a high-performance, cross-platform AI inference engine built with Rust and the Candle framework. It brings state-of-the-art AI models to your local machine—no API keys, no cloud dependencies, just pure, fast AI running directly on your hardware. aha is a high-performance, cross-platform AI inference engine built with Rust and the Candle framework. It brings state-of-the-art AI models to your local machine—no API keys, no cloud dependencies, just pure, fast AI running directly on your hardware.
## Changelog ## Changelog
### v0.2.5 (2026-03-30)
- add LFM2.5VL-1.6B
- add LFM2VL-1.6B
### v0.2.4 (2026-03-23) ### v0.2.4 (2026-03-23)
- add LFM2.5-1.2B-Instruct - add LFM2.5-1.2B-Instruct
- add LFM2-1.2B - add LFM2-1.2B
@@ -43,17 +47,6 @@ aha is a high-performance, cross-platform AI inference engine built with Rust an
### 2026-03-16 ### 2026-03-16
- Added Qwen3.5 mmproj - Added Qwen3.5 mmproj
### 2026-03-14
- update rust version
- Added Qwen3.5 gguf support, but the 4B model still has issues; to be resolved.
### v0.2.2 (2026-03-07)
- Added GLM-OCR model
### v0.2.1 (2026-03-05)
- Added Qwen3.5 model
**[View full changelog](docs/changelog.md)** → **[View full changelog](docs/changelog.md)** →
## Quick Start ## Quick Start
@@ -127,8 +120,8 @@ curl http://localhost:10100/chat/completions \
| Category | Models | | Category | Models |
|----------|--------| |----------|--------|
| **Text** | Qwen3, MiniCPM4, <br> LFM2-1.2B, LFM2.5-1.2B-Instruct | | **Text** | Qwen3, MiniCPM4, <br> LFM2-1.2B, LFM2.5-1.2B-Instruct |
| **Vision** | Qwen2.5-VL, Qwen3-VL, Qwen3.5 | | **Vision** | Qwen2.5-VL, Qwen3-VL, Qwen3.5, <br> LFM2.5-VL-1.6B, LFM2-VL-1.6B |
| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 , <br> , PaddleOCR-VL, PaddleOCR-VL1.5, <br> Hunyuan-OCR, GLM-OCR | | **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 , <br> PaddleOCR-VL, PaddleOCR-VL1.5, <br> Hunyuan-OCR, GLM-OCR |
| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR | | **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
| **Audio** | VoxCPM, VoxCPM1.5 | | **Audio** | VoxCPM, VoxCPM1.5 |
| **Image** | RMBG-2.0 (background removal) | | **Image** | RMBG-2.0 (background removal) |
+6 -14
View File
@@ -25,6 +25,10 @@
aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理引擎。将最先进的 AI 模型带到您的本地机器——无需 API 密钥,无需云依赖,纯粹、快速的 AI,直接在您的硬件上运行。 aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理引擎。将最先进的 AI 模型带到您的本地机器——无需 API 密钥,无需云依赖,纯粹、快速的 AI,直接在您的硬件上运行。
## 更新日志 ## 更新日志
### v0.2.5 (2026-03-30)
- 新增 LFM2.5VL-1.6B
- 新增 LFM2VL-1.6B
### v0.2.4 (2026-03-23) ### v0.2.4 (2026-03-23)
- 新增 LFM2.5-1.2B-Instruct - 新增 LFM2.5-1.2B-Instruct
- 新增 LFM2-1.2B - 新增 LFM2-1.2B
@@ -43,18 +47,6 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理
### 2026-03-16 ### 2026-03-16
- 增加 Qwen3.5 mmproj - 增加 Qwen3.5 mmproj
### 2026-03-14
- 更新rust版本
- 增加了对 Qwen3.5 gguf 的支持,但 4B 模型仍然存在问题;待解决。
### v0.2.2 (2026-03-07)
- 新增GLM-OCR 模型
### v0.2.1 (2026-03-05)
- 新增Qwen3.5 模型
### 2026-03-01
- 更新 interpolate.rs
**[查看完整更新日志](docs/changelog.zh-CN.md)** → **[查看完整更新日志](docs/changelog.zh-CN.md)** →
@@ -129,8 +121,8 @@ curl http://localhost:10100/chat/completions \
| 类别 | 模型 | | 类别 | 模型 |
|------|------| |------|------|
| **文本** | Qwen3, MiniCPM4, <br> LFM2-1.2B, LFM2.5-1.2B-Instruct | | **文本** | Qwen3, MiniCPM4, <br> LFM2-1.2B, LFM2.5-1.2B-Instruct |
| **视觉** | Qwen2.5-VL, Qwen3-VL, Qwen3.5 | | **视觉** | Qwen2.5-VL, Qwen3-VL, Qwen3.5 <br> LFM2.5-VL-1.6B, LFM2-VL-1.6B |
| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 , <br> , PaddleOCR-VL, PaddleOCR-VL1.5, <br> Hunyuan-OCR, GLM-OCR | | **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 , <br> PaddleOCR-VL, PaddleOCR-VL1.5, <br> Hunyuan-OCR, GLM-OCR |
| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano,Qwen3-ASR | | **ASR** | GLM-ASR-Nano, Fun-ASR-Nano,Qwen3-ASR |
| **音频** | VoxCPM, VoxCPM1.5 | | **音频** | VoxCPM, VoxCPM1.5 |
| **图像** | RMBG-2.0 (背景移除) | | **图像** | RMBG-2.0 (背景移除) |
+4
View File
@@ -5,6 +5,10 @@ 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/), 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). and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
### v0.2.5 (2026-03-30)
- add LFM2.5VL-1.6B
- add LFM2VL-1.6B
### v0.2.4 (2026-03-23) ### v0.2.4 (2026-03-23)
- add LFM2.5-1.2B-Instruct - add LFM2.5-1.2B-Instruct
- add LFM2-1.2B - add LFM2-1.2B
+4
View File
@@ -5,6 +5,10 @@
格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.0.0/) 格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.0.0/)
本项目遵循 [语义化版本](https://semver.org/lang/zh-CN/spec/v2.0.0.html)。 本项目遵循 [语义化版本](https://semver.org/lang/zh-CN/spec/v2.0.0.html)。
### v0.2.5 (2026-03-30)
- 新增 LFM2.5VL-1.6B
- 新增 LFM2VL-1.6B
### v0.2.4 (2026-03-23) ### v0.2.4 (2026-03-23)
- 新增 LFM2.5-1.2B-Instruct - 新增 LFM2.5-1.2B-Instruct
- 新增 LFM2-1.2B - 新增 LFM2-1.2B