●Change8

Migrating to llama.cpp b8911

Version b8911 introduces 2 breaking changes. This guide details how to update your code.

Released: 4/24/2026

2
Breaking Changes
2
Migration Steps
6
Affected Symbols

⚠️ Check Your Code

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

HTP_OPMASK_QUEUEopmaskopstageopsyncggml/src/ggml-hexagon/htp/htp-ops.hscripts/snapdragon/ggml-hexagon-profile.py

Breaking Changes

●Issue #1

The name of the opmask configuration was changed to opstage. If you were using 'opmask', you must now use 'opstage'.

●Issue #2

The 'opsync' mechanism is removed because the profiler is now fully asynchronous. Code relying on 'opsync' will need refactoring.

Migration Steps

  1. 1
    Rename any usage of 'opmask' to 'opstage'.
  2. 2
    Remove any reliance on the 'opsync' mechanism due to its removal.

Release Summary

This release significantly enhances Hexagon backend capabilities by adding comprehensive Op profiling support, including PMU integration and asynchronous operation handling. Several internal naming conventions were updated, such as renaming 'opmask' to 'opstage' and removing 'opsync'.

Need More Details?

View the full release notes and all changes for llama.cpp b8911.

View Full Changelog