Change8

b10310

Breaking Changes
📦 llama-cppView on GitHub →
1 breaking🐛 2 fixes🔧 3 symbols

Summary

This release introduces aarch64 HWCAP fallbacks and fixes fp16 variant detection in ggml. It also renames the `has_fp16_va` field to `has_fp16` for better clarity on the FEAT_FP16 extension.

⚠️ Breaking Changes

  • The `has_fp16_va` field has been renamed to `has_fp16`. This change gates the entire FEAT_FP16 extension, including scalar and vector half-precision arithmetic.

Migration Steps

  1. Update code that references `has_fp16_va` to use `has_fp16` instead.

🐛 Bug Fixes

  • Added fallback definitions for missing aarch64 HWCAP bits.
  • Required HWCAP_ASIMDHP for aarch64 fp16 CPU variants.

Affected Symbols