runtime-llamacpp-v0.1.3
dstotijn/hettyruntime-llamacpp-v0.1.3Jun 28, 2026by LauraGPT
AI Summary
This release rebuilds the runtime binaries with conservative CPU instruction flags to resolve compatibility issues such as Illegal Instruction (SIGILL) errors.
Key Highlights
- Rebuilds with conservative CPU flags to prevent crashes
- Disables ggml native CPU tuning and high-ISA flags
- Fixes crashes on 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`.