runtime-llamacpp-v0.1.4
sxyazi/yaziruntime-llamacpp-v0.1.4Jun 29, 2026by github-actions[bot]
AI Summary
Provides prebuilt self-contained binaries for the llama.cpp runtime supporting SenseVoice, Paraformer, and Fun-ASR-Nano with built-in VAD.
Key Highlights
- Self-contained binaries (no Python or build required)
- Supports SenseVoice, Paraformer, and Fun-ASR-Nano models
- Built-in FSMN-VAD (on-device ASR)
- Optimized assets: x64 for compatibility, x64-avx2 for throughput
New Features
- Prebuilt x64 and x64-avx2 binaries
- Model support: SenseVoice, Paraformer, Fun-ASR-Nano
- Built-in VAD functionality
Full Release Notes
Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime — SenseVoice, Paraformer and Fun-ASR-Nano with built-in FSMN-VAD (a whisper.cpp-style on-device ASR, strong on Chinese). Get a model with `bash download-funasr-model.sh <sensevoice|paraformer|nano>`, then run `llama-funasr-cli` / `llama-funasr-sensevoice` / `llama-funasr-paraformer`. Use the default x64 asset for maximum CPU compatibility; use the x64-avx2 asset on CPUs with AVX2/FMA/F16C/BMI2 for higher throughput. No Python, no build. Docs: runtime/llama.cpp/README.md