runtime-llamacpp-v0.1.3

luminal-ai/luminalruntime-llamacpp-v0.1.3Jun 28, 2026by LauraGPT

AI Summary

Rebuilds the v0.1.2 runtime with conservative CPU flags to prevent crashes caused by unsupported instruction sets like AVX/AVX2/AVX512.

Key Highlights

Disables native CPU tuning and high-ISA flags to prevent crashes.
Fixes Illegal instruction, SIGILL, and Windows error 0xC000001D.
Ensures portability across different CPU architectures.

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`.