Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.9

KeygraphHQ/shannonruntime-llamacpp-v0.1.9Jul 24, 2026by LauraGPT

AI Summary

This release updates the FunASR llama.cpp runtime to v0.1.9, featuring prebuilt binaries for various platforms and incorporating a critical security fix for the YAML loader in the SenseVoice source snapshot.

Key Highlights

  • Includes a security fix for the YAML loader by moving the SenseVoice source to the main branch.
  • Provides prebuilt binaries for Linux, Windows, ARM64, and macOS with multiple backend options (AVX2, Vulkan, CUDA).
  • Supports SenseVoice, Paraformer, Fun-ASR-Nano, and includes built-in FSMN-VAD.
  • Requires no Python runtime or local compilation to run.

New Features

  • Security update: Replaced unsafe YAML loader with `yaml.SafeLoader`.
  • Model support: SenseVoice, Paraformer, and Fun-ASR-Nano.
  • Audio processing: Built-in FSMN-VAD.
  • Hardware acceleration: Vulkan backend support.
  • Cross-platform distribution: Native packages for Linux, Windows, ARM64, and macOS.

Full Release Notes

Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime, with SenseVoice, Paraformer, and Fun-ASR-Nano support plus built-in FSMN-VAD.

This release moves the SenseVoice **Latest Release** source snapshot onto current `main`, including the `yaml.SafeLoader` security fix from [#312](https://github.com/QwenAudio/SenseVoice/pull/312). Users downloading GitHub's generated source archives no longer receive the older unsafe YAML loader from `runtime-llamacpp-v0.1.4`.

## Choose an asset

- Default `linux-x64` / `windows-x64`: maximum CPU compatibility.
- `linux-x64-avx2` / `windows-x64-avx2`: higher throughput on CPUs with AVX2, FMA, F16C, and BMI2.
- `linux-x64-vulkan` / `windows-x64-vulkan`: Vulkan backend; requires a working Vulkan driver and ICD.
- `windows-x64-cuda`: CUDA backend targeting architecture 86; build from source for other GPU architectures.
- Native `linux-arm64` and `macos-arm64` packages are included.

Download a default quantized model with:

```bash
pip install -U huggingface_hub
bash download-funasr-model.sh sensevoice
```

Then run `llama-funasr-sensevoice`; no Python ASR runtime or local compilation is required.

All nine files are byte-for-byte identical to the digest-verified assets from [`modelscope/FunASR` runtime v0.1.9](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.1.9).

Documentation: https://github.com/QwenAudio/SenseVoice/blob/runtime-llamacpp-v0.1.9/runtime/llama.cpp/README.md