●Change8

Migrating to llama.cpp b9784

Version b9784 introduces 2 breaking changes. This guide details how to update your code.

Released: 6/24/2026

2
Breaking Changes
2
Migration Steps
11
Affected Symbols

⚠️ Check Your Code

If you use any of these symbols, you need to read this guide:

MUL_MATMUL_MAT_IDhex-mmhvx-mmhmx-mmvec_dotsqweightvtcm_weightkernel-paramsmatmul-ops.hGGML_HEXAGON_MM_SELECT

Breaking Changes

●Issue #1

Support for hardware architecture versions older than v73 has been removed because HMX is now required for most use-cases.

●Issue #2

The new tiled repack format (renamed from x4x2) is now permanent; older formats are removed.

Migration Steps

  1. 1
    Ensure target hardware architecture is v73 or newer, as support for older architectures is dropped.
  2. 2
    Update build system to use the new tiled repack format (formerly x4x2) consistently.

Release Summary

This release introduces a major rework of hexagon matrix multiplication (MUL_MAT/MUL_MAT_ID) with new tiled weight repacking and performance optimizations across HVX and HMX backends. Support for hardware older than architecture v73 has been removed.

Need More Details?

View the full release notes and all changes for llama.cpp b9784.

View Full Changelog