runtime-llamacpp-v0.1.4

QwenAudio/SenseVoiceruntime-llamacpp-v0.1.4Jun 29, 2026by LauraGPT

AI Summary

Prebuilt self-contained binaries for the FunASR llama.cpp runtime with added explicit AVX2 assets for better performance. This release addresses SIGILL issues and provides optimized options for high-performance CPUs.

Key Highlights

Added explicit `x64-avx2` assets for CPUs with AVX2/FMA/F16C/BMI2.
Addresses the SIGILL (Illegal instruction) issues found in previous versions.
Recommended for machines where v0.1.3 was too slow.
Default x64 package remains conservative for maximum CPU compatibility.

New Features

AVX2 optimized binaries
Performance tuning for compatible CPUs
Instruction set compatibility improvements

Full Release Notes

Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime.

This release keeps the default x64 assets conservative for maximum CPU compatibility and adds explicit `x64-avx2` assets for CPUs with AVX2/FMA/F16C/BMI2. If v0.1.3 fixed SIGILL but was too slow on your machine, try `funasr-llamacpp-windows-x64-avx2.zip`.

Use the default x64 package if the AVX2 package fails with `Illegal instruction` / `SIGILL`.