runtime-llamacpp-v0.1.1
kubernetes-sigs/agent-sandboxruntime-llamacpp-v0.1.1Jun 20, 2026by github-actions[bot]
AI Summary
Release of prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime, providing SenseVoice, Paraformer, and Fun-ASR-Nano models with built-in FSMN-VAD, requiring no Python or build environment.
Key Highlights
- Prebuilt self-contained binaries for llama.cpp / GGUF runtime
- Supports SenseVoice, Paraformer, and Fun-ASR-Nano
- Includes built-in FSMN-VAD
- No Python dependency; no build required
New Features
- SenseVoice model support
- Paraformer model support
- Fun-ASR-Nano model support
- FSMN-VAD integration
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`. No Python, no build. Docs: runtime/llama.cpp/README.md