Skip to content

FunASR llama.cpp runtime v0.2.1

Latest
Latest

Choose a tag to compare

View all tags
@github-actions github-actions released this 26 Aug 17:33
· 1 commit to main since this release
runtime-llamacpp-v0.2.1
c69e69a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

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

v0.2.1

  • Fixes Vulkan backend selection when the requested device is reported as an integrated GPU (GGML_BACKEND_DEVICE_TYPE_IGPU).
  • If both matching devices are available, the runtime prefers a discrete GPU and falls back to the integrated GPU.
  • The Windows Vulkan package is ready for real-hardware retesting on Radeon 780M. This release does not claim that unreported driver-specific failures are resolved.
  • The separate Radeon RX 9070 XT 0xC0000005 backend-initialization crash remains under investigation and is not claimed fixed by this selector change.
  • Android/Mali is not an official prebuilt or validated target in this release.

Quick start

Download the default quantized model with:

bash download-funasr-model.sh <sensevoice|paraformer|nano>

The helper requires the Hugging Face CLI (pip install -U huggingface_hub). Then run llama-funasr-cli, llama-funasr-sensevoice, or llama-funasr-paraformer.

Use the default x64 asset for maximum CPU compatibility. Use x64-avx2 on CPUs with AVX2/FMA/F16C/BMI2. The Vulkan assets require a working Vulkan driver/ICD and accelerate SenseVoiceSmall with --backend vulkan. The Windows CUDA asset targets CUDA architecture 86 and requires a compatible NVIDIA driver; build from source for other GPU architectures.

SHA-256

9657e519986a5db72082aab508439559987fd4e563733d11da4662f898c75c45  funasr-llamacpp-linux-arm64.tar.gz
32e459673297fc01fcda6901ca7d63cc9e64896a43a3c9edcb7a8e1ef70fcd04  funasr-llamacpp-linux-x64-avx2.tar.gz
d45d3acb77e05c4bae94d818ed4a5c66852be87b22c52723bd576377c055c6e6  funasr-llamacpp-linux-x64-vulkan.tar.gz
1bc83dd36d11b1a2b9a45faaf77a5d1014000ac641c93dfec73d24d71ec51caf  funasr-llamacpp-linux-x64.tar.gz
bc63c4d4b96f2465f1d258600668a971f4f600d661f1859b03797cefaa417167  funasr-llamacpp-macos-arm64.tar.gz
67e428a91614f8a0c1d53dc2d79cce8efc7916c030ae2ddce2cbcf667ec1c502  funasr-llamacpp-windows-x64-avx2.zip
af32e0ef352880fcfd5589e0152c44038bc81f462f42c7a6ca91a0d9879bac58  funasr-llamacpp-windows-x64-cuda.zip
5fd179c6aefc18477eb79fa6235c70d131a96eba621318bb84e901ae85035578  funasr-llamacpp-windows-x64-vulkan.zip
b8f2b8f241b57921d82d64068d9b5695629779f3db5f3205a730cb3810232bb4  funasr-llamacpp-windows-x64.zip

Build evidence: https://github.com/modelscope/FunASR/actions/runs/32991388379

Docs: https://github.com/modelscope/FunASR/blob/runtime-llamacpp-v0.2.1/runtime/llama.cpp/README.md

Assets 11
Loading