runtime-llamacpp-v0.1.3

docling-project/doclingruntime-llamacpp-v0.1.3Jun 28, 2026by LauraGPT

AI Summary

This release is a portable rebuild of the runtime designed to fix crashes caused by illegal instructions or Windows errors. It disables high-level CPU instruction flags and native tuning to ensure compatibility across different hardware environments.

Key Highlights

Fixes SIGILL and Windows error 0xC000001D crashes.
Disables high-ISA flags (AVX, AVX2, AVX512, VNNI, FMA, F16C, BMI2) for compatibility.
Rebuilds v0.1.2 with conservative CPU flags to avoid GitHub Actions runner dependencies.

New Features

Generic CPU compatibility for portable binaries.
Rebuild to resolve instruction set dependency issues.

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`.