runtime-llamacpp-v0.1.9: nine Linux, macOS and Windows packages #157
LauraGPT
announced in
Announcements
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime, with Fun-ASR-Nano, SenseVoice, and Paraformer support plus built-in FSMN-VAD.
This release updates the Fun-ASR Latest Release from runtime v0.1.4 to v0.1.9 and adds the previously missing Vulkan and Windows CUDA packages. Its source snapshot also contains the corrected bilingual vLLM guide: users now clone the canonical
modelscope/FunASRservice scripts before runningserve_vllm.pyorserve_realtime_ws.py.Choose an asset
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.linux-arm64andmacos-arm64packages are included.Download a default quantized model with:
Then run
llama-funasr-cli; no Python ASR runtime or local compilation is required.All nine files are byte-for-byte identical to the digest-verified assets from
modelscope/FunASRruntime v0.1.9.Documentation: https://github.com/QwenAudio/Fun-ASR/blob/runtime-llamacpp-v0.1.9/runtime/llama.cpp/README.md
中文摘要:v0.1.9 现在直接提供 9 个 Linux、macOS 和 Windows 预编译包,补齐 Vulkan 和 Windows CUDA;无需 Python ASR 运行时或本地编译。请选择与 CPU/GPU 和驱动匹配的资产,并按 release 页面提供的 SHA-256 摘要校验下载。
Questions and real deployment results are welcome in this thread. If Fun-ASR-Nano is useful, follow or star the repository: https://github.com/QwenAudio/Fun-ASR
Exact assets / 完整附件
All reactions