runtime-llamacpp-v0.1.3

Tencent/WeKnoraruntime-llamacpp-v0.1.3Jun 28, 2026by LauraGPT

AI Summary

Portable rebuild of the FunASR llama.cpp runtime binaries with conservative CPU flags to ensure compatibility with generic hardware.

Key Highlights

Disables native CPU tuning and high-ISA flags (AVX/AVX2/AVX512, etc.)
Fixes crashes caused by Illegal instruction (SIGILL) or Windows error 0xC000001D
Targets generic x64 assets to avoid dependency on GitHub Actions runner instruction sets

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`.