runtime-llamacpp-v0.1.4

docling-project/doclingruntime-llamacpp-v0.1.4Jun 29, 2026by LauraGPT

AI Summary

This release provides prebuilt self-contained binaries for the FunASR llama.cpp runtime. It optimizes CPU compatibility by offering conservative x64 assets alongside explicit AVX2/FMA/F16C/BMI2 assets to improve performance for compatible hardware while addressing SIGILL crashes.

Key Highlights

Added explicit `x64-avx2` assets for CPUs with AVX2/FMA/F16C/BMI2 support.
Addresses SIGILL crashes and performance issues from previous versions.
Provides conservative default x64 assets for maximum CPU compatibility.

New Features

Optimized binary distribution for x64-avx2 instruction sets.
Improved stability for generic x64 architectures.

Full Release Notes

Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime.

This release keeps the default x64 assets conservative for maximum CPU compatibility and adds explicit `x64-avx2` assets for CPUs with AVX2/FMA/F16C/BMI2. If v0.1.3 fixed SIGILL but was too slow on your machine, try `funasr-llamacpp-windows-x64-avx2.zip`.

Use the default x64 package if the AVX2 package fails with `Illegal instruction` / `SIGILL`.