●Change8

Migrating to llama.cpp b8682

Version b8682 introduces 2 breaking changes. This guide details how to update your code.

Released: 4/6/2026

2
Breaking Changes
1
Migration Steps
3
Affected Symbols

⚠️ Check Your Code

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

Q1_0Q1_0_g128LlamaFileType Enum

Breaking Changes

●Issue #1

The quantization type previously named Q1_0 (group size 32) has been removed.

●Issue #2

The quantization type previously named Q1_0_g128 has been renamed to Q1_0.

Migration Steps

  1. 1
    If you were using the old Q1_0 (group size 32) quantization, you must update your model loading logic to use the new Q1_0 (which corresponds to the old Q1_0_g128).

Release Summary

This release introduces Q1_0 1-bit quantization support for the CPU, involving renaming and removing specific quantization variants and fixing related enum issues.

Need More Details?

View the full release notes and all changes for llama.cpp b8682.

View Full Changelog