aha

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

Installation

git clone https://github.com/jhqxxx/aha.git
cd aha
cargo build --release

Optional Features:

# CUDA (NVIDIA GPU acceleration)
cargo build --release --features cuda

# Metal (Apple GPU acceleration for macOS)
cargo build --release --features metal

# Flash Attention (faster inference)
cargo build --release --features cuda,flash-attn

# FFmpeg (multimedia processing)
cargo build --release --features ffmpeg

CLI Quick Reference

# List all supported models
aha list

# Download model only
aha download -m Qwen/Qwen3-ASR-0.6B

# Download model and start service
aha cli -m Qwen/Qwen3-ASR-0.6B

# Run inference directly (without starting service)
aha run -m Qwen/Qwen3-ASR-0.6B -i "audio.wav"

# Run local all-MiniLM-L6-v2 embedding (native safetensors)
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2

# Start service only (model already downloaded)
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100

Chat

aha serv -m Qwen/Qwen3-0.6B -p 10100

Then use the unified (OpenAI-compatible) API:

curl http://localhost:10100/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-0.6B",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }
'

aha-ui

cd aha-ui

use npm

install npm

refer to https://nodejs.org/en/download

# Download and install nvm:
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.4/install.sh | bash
# in lieu of restarting the shell
\. "$HOME/.nvm/nvm.sh"
# Download and install Node.js:
nvm install 24
# Verify the Node.js version:
node -v # Should print "v24.15.0".
# Verify npm version:
npm -v # Should print "11.12.1".

npm run aha-ui

# Make sure in the aha-ui directory
# and make sure that aha has been compiled
npm install
npm run tauri dev

npm build & install & run

npm run tauri build
# target in
# -- aha-ui/src-tauri/target/release/bundle/deb/aha-ui_0.1.0_amd64.deb
# -- aha-ui/src-tauri/target/release/bundle/rpm/aha-ui-0.1.0-1.x86_64.rpm
# -- aha-ui/src-tauri/target/release/bundle/appimage/aha-ui_0.1.0_amd64.AppImage

use pnpm

install pnpm

curl -fsSL https://get.pnpm.io/install.sh | sh -

pnpm run aha-ui

# Make sure in the aha-ui directory
# and make sure that aha has been compiled
pnpm run tauri dev

pnpm build & install & run

pnpm run tauri build
# target in
# -- aha-ui/src-tauri/target/release/bundle/deb/aha-ui_0.1.0_amd64.deb
# -- aha-ui/src-tauri/target/release/bundle/rpm/aha-ui-0.1.0-1.x86_64.rpm
# -- aha-ui/src-tauri/target/release/bundle/appimage/aha-ui_0.1.0_amd64.AppImage

Documentation

Development

Using aha as a Library

cargo add aha

// VoxCPM example
use aha::models::voxcpm::generate::VoxCPMGenerate;
use aha::utils::audio_utils::save_wav_mono;
use anyhow::Result;

fn main() -> Result<()> {
    let model_path = "xxx/OpenBMB/VoxCPM2/";

    let mut voxcpm_generate = VoxCPMGenerate::init(model_path, None, None)?;
    let generate = voxcpm_generate.inference(
        "aha是一个基于Rust和Candle框架的本地AI推理引擎，支持多模态模型（文本、视觉、语音、OCR）。".to_string(),
        None,
        None,
        2,
        1000,
        10,
        2.0,
        6.0,
    )?;

    save_wav_mono(&generate, "voxcpm2.wav", voxcpm_generate.sample_rate() as u32)?;
    Ok(())
}

Extending New Models

• Create new model file in src/models/
• Export in src/models/mod.rs
• Add support for CLI model inference in src/exec/
• Add tests and examples in tests/

Features

• High-performance inference via Candle framework
• Multi-modal model support (vision, language, speech)
• Clean, easy-to-use API design
• Minimal dependencies, compact binaries
• Flash Attention support for long sequences
• FFmpeg support for multimedia processing

License

Apache-2.0 — See LICENSE for details.

Acknowledgments

• Candle - Excellent Rust ML framework
• All model authors and contributors

Wechat & Donate

Wechat Group	Donate

Built with ❤️ by the aha team

We're continuously expanding our model support. Contributions are welcome!

If this project helps you, please consider giving us a ⭐ Star!