From 899b1e7dfa8addc424aa10f5d9318af3bf36b705 Mon Sep 17 00:00:00 2001
From: jhqxxx <18280426169@163.com>
Date: Tue, 31 Mar 2026 18:59:57 +0800
Subject: [PATCH] update doc
---
README.md | 94 ++++++++++++++++++----------------
README.zh-CN.md | 94 +++++++++++++++++-----------------
docs/installation.md | 69 ++++++++++++-------------
docs/installation.zh-CN.md | 54 +++++++++++--------
docs/supported-models.md | 37 +++++++++++++
docs/supported-models.zh-CN.md | 37 +++++++++++++
src/api/mod.rs | 29 -----------
7 files changed, 236 insertions(+), 178 deletions(-)
diff --git a/README.md b/README.md
index c8e7ce7..9ea5982 100644
--- a/README.md
+++ b/README.md
@@ -24,36 +24,26 @@
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
-### 2026-03-31
-- aha model name use modelscope id replace
-- update WhichModel
-- Usage add time info
-- dependencies delete aha_openai_dive,chrono
-### v0.2.5 (2026-03-30)
-- add LFM2.5VL-1.6B
-- add LFM2VL-1.6B
+### Supported Models
-### v0.2.4 (2026-03-23)
-- add LFM2.5-1.2B-Instruct
-- add LFM2-1.2B
+| Category | Models |
+|----------|--------|
+| **Text** | Qwen3, MiniCPM4,
LFM2, LFM2.5 |
+| **Vision** | Qwen2.5-VL, Qwen3-VL, Qwen3.5,
LFM2.5-VL, LFM2-VL |
+| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 ,
PaddleOCR-VL, PaddleOCR-VL1.5,
Hunyuan-OCR, GLM-OCR |
+| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
+| **Audio** | VoxCPM, VoxCPM1.5 |
+| **Image** | RMBG-2.0 (background removal) |
-### v0.2.3 (2026-03-18)
-- add DeepSeek-OCR-2
-
-### 2026-03-17
-- add PaddleOCR-VL1.5 model
-- 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 GGUF loading)
-- WhichModel add qwen3.5-gguf
-
-### 2026-03-16
-- Added Qwen3.5 mmproj
-
-**[View full changelog](docs/changelog.md)** →
+## Why aha?
+- **🚀 High-Performance Inference** - Powered by Candle framework for efficient tensor computation and model inference
+- **🔧 Unified Interface** — One tool for text, vision, speech, and OCR
+- **📦 Local-First** — All processing runs locally, no data leaves your machine
+- **🎯 Cross-Platform** — Works on Linux, macOS, and Windows
+- **⚡ GPU Accelerated** — Optional CUDA support for faster inference
+- **🛡️ Memory Safe** — Built with Rust for reliability
+- **🧠 Attention Optimization** - Optional Flash Attention support for optimized long sequence processing
## Quick Start
@@ -111,7 +101,7 @@ aha serv -m Qwen/Qwen3-0.6B -p 10100
Then use the unified (OpenAI-compatible) API:
```bash
-curl http://localhost:10100/chat/completions \
+curl http://localhost:10100/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-0.6B",
@@ -121,16 +111,38 @@ curl http://localhost:10100/chat/completions \
'
```
-### Supported Models
+## Changelog
+
+### 2026-03-31
+- aha model name use modelscope id replace
+- update WhichModel
+- Usage add time info
+- dependencies delete aha_openai_dive,chrono
+
+### v0.2.5 (2026-03-30)
+- add LFM2.5VL-1.6B
+- add LFM2VL-1.6B
+
+### v0.2.4 (2026-03-23)
+- add LFM2.5-1.2B-Instruct
+- add LFM2-1.2B
+
+### v0.2.3 (2026-03-18)
+- add DeepSeek-OCR-2
+
+### 2026-03-17
+- add PaddleOCR-VL1.5 model
+- 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 GGUF loading)
+- WhichModel add qwen3.5-gguf
+
+### 2026-03-16
+- Added Qwen3.5 mmproj
+
+**[View full changelog](docs/changelog.md)** →
-| Category | Models |
-|----------|--------|
-| **Text** | Qwen3, MiniCPM4,
LFM2, LFM2.5 |
-| **Vision** | Qwen2.5-VL, Qwen3-VL, Qwen3.5,
LFM2.5-VL, LFM2-VL |
-| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 ,
PaddleOCR-VL, PaddleOCR-VL1.5,
Hunyuan-OCR, GLM-OCR |
-| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
-| **Audio** | VoxCPM, VoxCPM1.5 |
-| **Image** | RMBG-2.0 (background removal) |
## Documentation
@@ -145,14 +157,6 @@ curl http://localhost:10100/chat/completions \
| [Development](docs/development.md) | Contributing guide |
| [Changelog](docs/changelog.md) | Version history |
-## Why aha?
-- **🚀 High-Performance Inference** - Powered by Candle framework for efficient tensor computation and model inference
-- **🔧 Unified Interface** — One tool for text, vision, speech, and OCR
-- **📦 Local-First** — All processing runs locally, no data leaves your machine
-- **🎯 Cross-Platform** — Works on Linux, macOS, and Windows
-- **⚡ GPU Accelerated** — Optional CUDA support for faster inference
-- **🛡️ Memory Safe** — Built with Rust for reliability
-- **🧠 Attention Optimization** - Optional Flash Attention support for optimized long sequence processing
## Development
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 12c0501..0f7a2d0 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -24,37 +24,25 @@
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
+### 支持的模型
-### 2026-03-31
-- aha模型名称使用 modelscope id 替换
-- 更新 WhichModel 枚举
-- Usage 增加时间信息
-- 删除 aha_openai_dive, chrono 依赖
+| 类别 | 模型 |
+|------|------|
+| **文本** | Qwen3, MiniCPM4,
LFM2, LFM2.5 |
+| **视觉** | Qwen2.5-VL, Qwen3-VL, Qwen3.5
LFM2.5-VL, LFM2-VL |
+| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 ,
PaddleOCR-VL, PaddleOCR-VL1.5,
Hunyuan-OCR, GLM-OCR |
+| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
+| **音频** | VoxCPM, VoxCPM1.5 |
+| **图像** | RMBG-2.0 (背景移除) |
-### v0.2.5 (2026-03-30)
-- 新增 LFM2.5VL-1.6B
-- 新增 LFM2VL-1.6B
-
-### v0.2.4 (2026-03-23)
-- 新增 LFM2.5-1.2B-Instruct
-- 新增 LFM2-1.2B
-
-### v0.2.3 (2026-03-18)
-- 新增 DeepSeek-OCR-2
-
-### 2026-03-17
-- 新增 PaddleOCR-VL1.5 模型
-- 修复 qwen3.5 position_ids 创建错误
-- cli 参数增加
- - gguf_path: 本地 GGUF 模型权重路径（加载 GGUF 模型时需要）
- - mmproj_path: 本地 mmproj GGUF 权重路径（加载多模态 GGUF 时需要）
-- WhichModel 增加 qwen3.5-gguf
-
-### 2026-03-16
-- 增加 Qwen3.5 mmproj
-
-**[查看完整更新日志](docs/changelog.zh-CN.md)** →
+## 为什么选择 aha？
+- **🚀 高性能推理** - 基于 Candle 框架，提供高效的张量计算和模型推理
+- **🔧 统一接口** — 一个工具搞定文本、视觉、语音和 OCR
+- **📦 本地优先** — 所有处理在本地运行，数据不离境
+- **🎯 跨平台** — 支持 Linux、macOS 和 Windows
+- **⚡ GPU 加速** — 可选 CUDA 支持以获得更快推理
+- **🛡️ 内存安全** — Rust 构建，稳定可靠
+- **🧠 注意力优化** - 可选 Flash Attention 支持，优化长序列处理
## 快速开始
@@ -112,7 +100,7 @@ aha serv -m Qwen/Qwen3-0.6B -p 10100
然后使用统一(兼容 OpenAI)的 API：
```bash
-curl http://localhost:10100/chat/completions \
+curl http://localhost:10100/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-0.6B",
@@ -121,18 +109,37 @@ curl http://localhost:10100/chat/completions \
}'
```
+## 更新日志
-### 支持的模型
+### 2026-03-31
+- aha模型名称使用 modelscope id 替换
+- 更新 WhichModel 枚举
+- Usage 增加时间信息
+- 删除 aha_openai_dive, chrono 依赖
-| 类别 | 模型 |
-|------|------|
-| **文本** | Qwen3, MiniCPM4,
LFM2, LFM2.5 |
-| **视觉** | Qwen2.5-VL, Qwen3-VL, Qwen3.5
LFM2.5-VL, LFM2-VL |
-| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2 ,
PaddleOCR-VL, PaddleOCR-VL1.5,
Hunyuan-OCR, GLM-OCR |
-| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano,Qwen3-ASR |
-| **音频** | VoxCPM, VoxCPM1.5 |
-| **图像** | RMBG-2.0 (背景移除) |
+### v0.2.5 (2026-03-30)
+- 新增 LFM2.5VL-1.6B
+- 新增 LFM2VL-1.6B
+### v0.2.4 (2026-03-23)
+- 新增 LFM2.5-1.2B-Instruct
+- 新增 LFM2-1.2B
+
+### v0.2.3 (2026-03-18)
+- 新增 DeepSeek-OCR-2
+
+### 2026-03-17
+- 新增 PaddleOCR-VL1.5 模型
+- 修复 qwen3.5 position_ids 创建错误
+- cli 参数增加
+ - gguf_path: 本地 GGUF 模型权重路径（加载 GGUF 模型时需要）
+ - mmproj_path: 本地 mmproj GGUF 权重路径（加载多模态 GGUF 时需要）
+- WhichModel 增加 qwen3.5-gguf
+
+### 2026-03-16
+- 增加 Qwen3.5 mmproj
+
+**[查看完整更新日志](docs/changelog.zh-CN.md)** →
## 文档
@@ -147,15 +154,6 @@ curl http://localhost:10100/chat/completions \
| [开发指南](docs/development.zh-CN.md) | 贡献指南 |
| [更新日志](docs/changelog.zh-CN.md) | 版本历史 |
-## 为什么选择 aha？
-- **🚀 高性能推理** - 基于 Candle 框架，提供高效的张量计算和模型推理
-- **🔧 统一接口** — 一个工具搞定文本、视觉、语音和 OCR
-- **📦 本地优先** — 所有处理在本地运行，数据不离境
-- **🎯 跨平台** — 支持 Linux、macOS 和 Windows
-- **⚡ GPU 加速** — 可选 CUDA 支持以获得更快推理
-- **🛡️ 内存安全** — Rust 构建，稳定可靠
-- **🧠 注意力优化** - 可选 Flash Attention 支持，优化长序列处理
-
## 开发
### aha 作为库使用
diff --git a/docs/installation.md b/docs/installation.md
index 9f712ea..3c3bca9 100644
--- a/docs/installation.md
+++ b/docs/installation.md
@@ -277,43 +277,42 @@ aha list
Expected output for `aha list`:
-```
+```shell
#Supported models:
-
- Available models:
+Available models:
-Model Name ModelScope ID
------------------------------------------------------------
-LiquidAI/LFM2-1.2B LiquidAI/LFM2-1.2B ✔
-LiquidAI/LFM2.5-1.2B-Instruct LiquidAI/LFM2.5-1.2B-Instruct ✔
-LiquidAI/LFM2.5-VL-1.6B LiquidAI/LFM2.5-VL-1.6B ✔
-LiquidAI/LFM2-VL-1.6B LiquidAI/LFM2-VL-1.6B ✔
-OpenBMB/MiniCPM4-0.5B OpenBMB/MiniCPM4-0.5B ✔
-Qwen/Qwen2.5-VL-3B-Instruct Qwen/Qwen2.5-VL-3B-Instruct ✔
-Qwen/Qwen2.5-VL-7B-Instruct Qwen/Qwen2.5-VL-7B-Instruct
-Qwen/Qwen3-0.6B Qwen/Qwen3-0.6B ✔
-Qwen/Qwen3.5-0.8B Qwen/Qwen3.5-0.8B ✔
-Qwen/Qwen3.5-2B Qwen/Qwen3.5-2B
-Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B
-Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B
-qwen3.5-gguf qwen3.5-gguf
-Qwen/Qwen3-ASR-0.6B Qwen/Qwen3-ASR-0.6B ✔
-Qwen/Qwen3-ASR-1.7B Qwen/Qwen3-ASR-1.7B
-Qwen/Qwen3-VL-2B-Instruct Qwen/Qwen3-VL-2B-Instruct ✔
-Qwen/Qwen3-VL-4B-Instruct Qwen/Qwen3-VL-4B-Instruct
-Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct
-Qwen/Qwen3-VL-32B-Instruct Qwen/Qwen3-VL-32B-Instruct
-deepseek-ai/DeepSeek-OCR deepseek-ai/DeepSeek-OCR ✔
-deepseek-ai/DeepSeek-OCR-2 deepseek-ai/DeepSeek-OCR-2
-Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan/HunyuanOCR ✔
-PaddlePaddle/PaddleOCR-VL PaddlePaddle/PaddleOCR-VL ✔
-PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle/PaddleOCR-VL-1.5
-AI-ModelScope/RMBG-2.0 AI-ModelScope/RMBG-2.0 ✔
-OpenBMB/VoxCPM-0.5B OpenBMB/VoxCPM-0.5B ✔
-OpenBMB/VoxCPM1.5 OpenBMB/VoxCPM1.5 ✔
-ZhipuAI/GLM-ASR-Nano-2512 ZhipuAI/GLM-ASR-Nano-2512 ✔
-FunAudioLLM/Fun-ASR-Nano-2512 FunAudioLLM/Fun-ASR-Nano-2512 ✔
-ZhipuAI/GLM-OCR ZhipuAI/GLM-OCR
+Model ID Owner type Download
+--------------------------------------------------------------------------------
+LiquidAI/LFM2-1.2B LiquidAI llm ✔
+LiquidAI/LFM2.5-1.2B-Instruct LiquidAI llm ✔
+LiquidAI/LFM2.5-VL-1.6B LiquidAI vlm ✔
+LiquidAI/LFM2-VL-1.6B LiquidAI vlm ✔
+OpenBMB/MiniCPM4-0.5B OpenBMB llm ✔
+Qwen/Qwen2.5-VL-3B-Instruct Qwen vlm ✔
+Qwen/Qwen2.5-VL-7B-Instruct Qwen vlm
+Qwen/Qwen3-0.6B Qwen llm ✔
+Qwen/Qwen3.5-0.8B Qwen vlm ✔
+Qwen/Qwen3.5-2B Qwen vlm
+Qwen/Qwen3.5-4B Qwen vlm
+Qwen/Qwen3.5-9B Qwen vlm
+qwen3.5-gguf none vlm
+Qwen/Qwen3-ASR-0.6B Qwen asr ✔
+Qwen/Qwen3-ASR-1.7B Qwen asr
+Qwen/Qwen3-VL-2B-Instruct Qwen vlm ✔
+Qwen/Qwen3-VL-4B-Instruct Qwen vlm
+Qwen/Qwen3-VL-8B-Instruct Qwen vlm
+Qwen/Qwen3-VL-32B-Instruct Qwen vlm
+deepseek-ai/DeepSeek-OCR deepseek-ai ocr ✔
+deepseek-ai/DeepSeek-OCR-2 deepseek-ai ocr
+Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan ocr ✔
+PaddlePaddle/PaddleOCR-VL PaddlePaddle ocr ✔
+PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+AI-ModelScope/RMBG-2.0 AI-ModelScope image ✔
+OpenBMB/VoxCPM-0.5B OpenBMB tts ✔
+OpenBMB/VoxCPM1.5 OpenBMB tts ✔
+ZhipuAI/GLM-ASR-Nano-2512 ZhipuAI asr ✔
+FunAudioLLM/Fun-ASR-Nano-2512 FunAudioLLM asr ✔
+ZhipuAI/GLM-OCR ZhipuAI ocr ✔
```
diff --git a/docs/installation.zh-CN.md b/docs/installation.zh-CN.md
index f309c0b..e7f0aea 100644
--- a/docs/installation.zh-CN.md
+++ b/docs/installation.zh-CN.md
@@ -279,28 +279,40 @@ aha list
```shell
#Supported models:
- Available models:
+Available models:
-Model Name ModelScope ID
------------------------------------------------------------
-OpenBMB/MiniCPM4-0.5B OpenBMB/MiniCPM4-0.5B
-Qwen/Qwen2.5-VL-3B-Instruct Qwen/Qwen2.5-VL-3B-Instruct
-Qwen/Qwen2.5-VL-7B-Instruct Qwen/Qwen2.5-VL-7B-Instruct
-Qwen/Qwen3-0.6B Qwen/Qwen3-0.6B
-Qwen/Qwen3-ASR-0.6B Qwen/Qwen3-ASR-0.6B
-Qwen/Qwen3-ASR-1.7B Qwen/Qwen3-ASR-1.7B
-Qwen/Qwen3-VL-4B-Instruct Qwen/Qwen3-VL-2B-Instruct
-Qwen/Qwen3-VL-4B-Instruct Qwen/Qwen3-VL-4B-Instruct
-Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct
-Qwen/Qwen3-VL-32B-Instruct Qwen/Qwen3-VL-32B-Instruct
-deepseek-ai/DeepSeek-OCR deepseek-ai/DeepSeek-OCR
-Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan/HunyuanOCR
-PaddlePaddle/PaddleOCR-VL PaddlePaddle/PaddleOCR-VL
-AI-ModelScope/RMBG-2.0 AI-ModelScope/RMBG-2.0
-voxcpm OpenBMB/VoxCPM-0.5B
-OpenBMB/VoxCPM1.5 OpenBMB/VoxCPM1.5
-ZhipuAI/GLM-ASR-Nano-2512 ZhipuAI/GLM-ASR-Nano-2512
-FunAudioLLM/Fun-ASR-Nano-2512 FunAudioLLM/Fun-ASR-Nano-2512
+Model ID Owner type Download
+--------------------------------------------------------------------------------
+LiquidAI/LFM2-1.2B LiquidAI llm ✔
+LiquidAI/LFM2.5-1.2B-Instruct LiquidAI llm ✔
+LiquidAI/LFM2.5-VL-1.6B LiquidAI vlm ✔
+LiquidAI/LFM2-VL-1.6B LiquidAI vlm ✔
+OpenBMB/MiniCPM4-0.5B OpenBMB llm ✔
+Qwen/Qwen2.5-VL-3B-Instruct Qwen vlm ✔
+Qwen/Qwen2.5-VL-7B-Instruct Qwen vlm
+Qwen/Qwen3-0.6B Qwen llm ✔
+Qwen/Qwen3.5-0.8B Qwen vlm ✔
+Qwen/Qwen3.5-2B Qwen vlm
+Qwen/Qwen3.5-4B Qwen vlm
+Qwen/Qwen3.5-9B Qwen vlm
+qwen3.5-gguf none vlm
+Qwen/Qwen3-ASR-0.6B Qwen asr ✔
+Qwen/Qwen3-ASR-1.7B Qwen asr
+Qwen/Qwen3-VL-2B-Instruct Qwen vlm ✔
+Qwen/Qwen3-VL-4B-Instruct Qwen vlm
+Qwen/Qwen3-VL-8B-Instruct Qwen vlm
+Qwen/Qwen3-VL-32B-Instruct Qwen vlm
+deepseek-ai/DeepSeek-OCR deepseek-ai ocr ✔
+deepseek-ai/DeepSeek-OCR-2 deepseek-ai ocr
+Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan ocr ✔
+PaddlePaddle/PaddleOCR-VL PaddlePaddle ocr ✔
+PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+AI-ModelScope/RMBG-2.0 AI-ModelScope image ✔
+OpenBMB/VoxCPM-0.5B OpenBMB tts ✔
+OpenBMB/VoxCPM1.5 OpenBMB tts ✔
+ZhipuAI/GLM-ASR-Nano-2512 ZhipuAI asr ✔
+FunAudioLLM/Fun-ASR-Nano-2512 FunAudioLLM asr ✔
+ZhipuAI/GLM-OCR ZhipuAI ocr ✔
```
diff --git a/docs/supported-models.md b/docs/supported-models.md
index 39d3b3f..0b4414b 100644
--- a/docs/supported-models.md
+++ b/docs/supported-models.md
@@ -2,6 +2,43 @@
aha supports a growing collection of state-of-the-art AI models across multiple domains.
+```shell
+Available models:
+
+Model ID Owner type Download
+--------------------------------------------------------------------------------
+LiquidAI/LFM2-1.2B LiquidAI llm ✔
+LiquidAI/LFM2.5-1.2B-Instruct LiquidAI llm ✔
+LiquidAI/LFM2.5-VL-1.6B LiquidAI vlm ✔
+LiquidAI/LFM2-VL-1.6B LiquidAI vlm ✔
+OpenBMB/MiniCPM4-0.5B OpenBMB llm ✔
+Qwen/Qwen2.5-VL-3B-Instruct Qwen vlm ✔
+Qwen/Qwen2.5-VL-7B-Instruct Qwen vlm
+Qwen/Qwen3-0.6B Qwen llm ✔
+Qwen/Qwen3.5-0.8B Qwen vlm ✔
+Qwen/Qwen3.5-2B Qwen vlm
+Qwen/Qwen3.5-4B Qwen vlm
+Qwen/Qwen3.5-9B Qwen vlm
+qwen3.5-gguf none vlm
+Qwen/Qwen3-ASR-0.6B Qwen asr ✔
+Qwen/Qwen3-ASR-1.7B Qwen asr
+Qwen/Qwen3-VL-2B-Instruct Qwen vlm ✔
+Qwen/Qwen3-VL-4B-Instruct Qwen vlm
+Qwen/Qwen3-VL-8B-Instruct Qwen vlm
+Qwen/Qwen3-VL-32B-Instruct Qwen vlm
+deepseek-ai/DeepSeek-OCR deepseek-ai ocr ✔
+deepseek-ai/DeepSeek-OCR-2 deepseek-ai ocr
+Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan ocr ✔
+PaddlePaddle/PaddleOCR-VL PaddlePaddle ocr ✔
+PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+AI-ModelScope/RMBG-2.0 AI-ModelScope image ✔
+OpenBMB/VoxCPM-0.5B OpenBMB tts ✔
+OpenBMB/VoxCPM1.5 OpenBMB tts ✔
+ZhipuAI/GLM-ASR-Nano-2512 ZhipuAI asr ✔
+FunAudioLLM/Fun-ASR-Nano-2512 FunAudioLLM asr ✔
+ZhipuAI/GLM-OCR ZhipuAI ocr ✔
+```
+
## Language Model
| Model | Parameters | Model Id | License |
diff --git a/docs/supported-models.zh-CN.md b/docs/supported-models.zh-CN.md
index d372fce..b451d02 100644
--- a/docs/supported-models.zh-CN.md
+++ b/docs/supported-models.zh-CN.md
@@ -2,6 +2,43 @@
aha 支持多个领域的最先进 AI 模型集合。
+```shell
+Available models:
+
+Model ID Owner type Download
+--------------------------------------------------------------------------------
+LiquidAI/LFM2-1.2B LiquidAI llm ✔
+LiquidAI/LFM2.5-1.2B-Instruct LiquidAI llm ✔
+LiquidAI/LFM2.5-VL-1.6B LiquidAI vlm ✔
+LiquidAI/LFM2-VL-1.6B LiquidAI vlm ✔
+OpenBMB/MiniCPM4-0.5B OpenBMB llm ✔
+Qwen/Qwen2.5-VL-3B-Instruct Qwen vlm ✔
+Qwen/Qwen2.5-VL-7B-Instruct Qwen vlm
+Qwen/Qwen3-0.6B Qwen llm ✔
+Qwen/Qwen3.5-0.8B Qwen vlm ✔
+Qwen/Qwen3.5-2B Qwen vlm
+Qwen/Qwen3.5-4B Qwen vlm
+Qwen/Qwen3.5-9B Qwen vlm
+qwen3.5-gguf none vlm
+Qwen/Qwen3-ASR-0.6B Qwen asr ✔
+Qwen/Qwen3-ASR-1.7B Qwen asr
+Qwen/Qwen3-VL-2B-Instruct Qwen vlm ✔
+Qwen/Qwen3-VL-4B-Instruct Qwen vlm
+Qwen/Qwen3-VL-8B-Instruct Qwen vlm
+Qwen/Qwen3-VL-32B-Instruct Qwen vlm
+deepseek-ai/DeepSeek-OCR deepseek-ai ocr ✔
+deepseek-ai/DeepSeek-OCR-2 deepseek-ai ocr
+Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan ocr ✔
+PaddlePaddle/PaddleOCR-VL PaddlePaddle ocr ✔
+PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+AI-ModelScope/RMBG-2.0 AI-ModelScope image ✔
+OpenBMB/VoxCPM-0.5B OpenBMB tts ✔
+OpenBMB/VoxCPM1.5 OpenBMB tts ✔
+ZhipuAI/GLM-ASR-Nano-2512 ZhipuAI asr ✔
+FunAudioLLM/Fun-ASR-Nano-2512 FunAudioLLM asr ✔
+ZhipuAI/GLM-OCR ZhipuAI ocr ✔
+```
+
## 文本生成
| 模型 | 参数量 | 模型id | 开源协议 |
diff --git a/src/api/mod.rs b/src/api/mod.rs
index d57340f..904810a 100644
--- a/src/api/mod.rs
+++ b/src/api/mod.rs
@@ -243,35 +243,6 @@ struct ErrorResponse {
error: String,
}
-// /// Get the owner/organization name for a model
-// fn which_model_to_owner(which_model: WhichModel) -> &'static str {
-// match which_model {
-// WhichModel::MiniCPM4_0_5B => "OpenBMB",
-// WhichModel::Qwen2_5VL3B | WhichModel::Qwen2_5VL7B => "Qwen",
-// WhichModel::Qwen3_0_6B | WhichModel::Qwen3ASR0_6B | WhichModel::Qwen3ASR1_7B => "Qwen",
-// WhichModel::Qwen3VL2B
-// | WhichModel::Qwen3VL4B
-// | WhichModel::Qwen3VL8B
-// | WhichModel::Qwen3VL32B
-// | WhichModel::Qwen3_5Gguf => "Qwen",
-// WhichModel::Qwen3_5_0_8B
-// | WhichModel::Qwen3_5_2B
-// | WhichModel::Qwen3_5_4B
-// | WhichModel::Qwen3_5_9B => "Qwen",
-// WhichModel::DeepSeekOCR | WhichModel::DeepSeekOCR2 => "deepseek-ai",
-// WhichModel::HunyuanOCR => "Tencent-Hunyuan",
-// WhichModel::PaddleOCRVL | WhichModel::PaddleOCRVL1_5 => "PaddlePaddle",
-// WhichModel::RMBG2_0 => "AI-ModelScope",
-// WhichModel::VoxCPM | WhichModel::VoxCPM1_5 => "OpenBMB",
-// WhichModel::GlmASRNano2512 | WhichModel::GlmOCR => "ZhipuAI",
-// WhichModel::FunASRNano2512 => "FunAudioLLM",
-// WhichModel::LFM2_1_2B
-// | WhichModel::LFM2_5_1_2BInstruct
-// | WhichModel::LFM2_5VL1_6B
-// | WhichModel::LFM2VL1_6B => "LiquidAI",
-// }
-// }
-
#[get("/models")]
pub(crate) async fn models() -> (Status, (ContentType, Json)) {
if let Some(model_ref) = MODEL.get() {