runtime-llamacpp-v0.2.1
fosrl/pangolinruntime-llamacpp-v0.2.1Aug 27, 2026by LauraGPT
Upgrading?
AI Summary
A prebuilt binary release of the FunASR llama.cpp runtime that fixes Vulkan GPU selection and provides multiple platform-specific archives for various hardware configurations.
Key Highlights
- Vulkan selection fix for integrated GPUs (prefers discrete, falls back to integrated).
- Nine platform-specific prebuilt binaries (Linux, macOS, Windows).
- Support for SenseVoice, Fun-ASR-Nano, and Paraformer models.
- Windows Vulkan package ready for Radeon 780M retesting.
New Features
- Vulkan selection logic improvement
- Prebuilt binaries for Linux, macOS, Windows (x64, arm64, avx2, vulkan, cuda)
- SenseVoice, Fun-ASR-Nano, and Paraformer model support
Full Release Notes
Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime, including SenseVoice, Fun-ASR-Nano, and Paraformer with built-in FSMN-VAD. ## v0.2.1 - Fixes Vulkan selection when a requested device is reported as an integrated GPU (`GGML_BACKEND_DEVICE_TYPE_IGPU`). - Prefers a matching discrete GPU and falls back to a matching integrated GPU. - Provides nine desktop archives for Linux, macOS, and Windows, including Vulkan and Windows CUDA variants. - The Windows Vulkan package is ready for Radeon 780M retesting. This selector fix does not claim to resolve the separate Radeon RX 9070 XT `0xC0000005` initialization crash. - Android/Mali is not an official prebuilt or validated target in this release. ## Quick start ```bash pip install -U huggingface_hub bash download-funasr-model.sh sensevoice ``` Then run `llama-funasr-sensevoice`. Use the default x64 asset for broad CPU compatibility, the x64-avx2 asset on CPUs with AVX2/FMA/F16C/BMI2, or a Vulkan/CUDA asset only with a compatible driver. The Windows CUDA asset targets architecture 86; build from source for other GPU architectures. ## Provenance These nine binaries are byte-for-byte identical to the digest-verified assets from the canonical [`modelscope/FunASR` runtime v0.2.1](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.1). They were built from exact FunASR commit `c69e69a0b78fb9becc8b2be91db8ae57d2a41f3c` by [Actions run 32991388379](https://github.com/modelscope/FunASR/actions/runs/32991388379). GitHub's generated source archives on this mirror tag are snapshots of the SenseVoice repository; use the canonical FunASR commit above for the native runtime source. Canonical documentation: https://www.funasr.com/en/deploy/llama-cpp.html ## SHA-256 ```text 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 ```
Related Repositories
openclaw/openclaw★ 392,716
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,091
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 359,523
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,818
The open source coding agent.
n8n-io/n8n★ 208,269
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.