runtime-llamacpp-v0.1.3
QuentinFuxa/WhisperLiveKitruntime-llamacpp-v0.1.3Jun 28, 2026by LauraGPT
AI Summary
A portable rebuild of the llama.cpp runtime binaries designed to fix compatibility issues with specific CPU instruction sets by disabling high-ISA flags.
Key Highlights
- Portable rebuild of the FunASR llama.cpp / GGUF runtime binaries
- Disables ggml native CPU tuning and high-ISA AVX/AVX2/AVX512 flags
- Fixes crashes caused by `Illegal instruction` or Windows error `0xC000001D`
Full Release Notes
Portable rebuild of the FunASR llama.cpp / GGUF runtime binaries. This release rebuilds the v0.1.2 runtime with conservative CPU flags for the generic x64 assets. In particular, it disables ggml native CPU tuning and high-ISA AVX/AVX2/AVX512/VNNI/FMA/F16C/BMI2 flags so the prebuilt binaries do not depend on the GitHub Actions runner CPU instruction set. Use this version if v0.1.2 crashes with `Illegal instruction`, `SIGILL`, or Windows error `0xC000001D`.