Change8

Migrating to llama.cpp b8957

Version b8957 introduces 1 breaking change. This guide details how to update your code.

Released: 4/28/2026

1
Breaking Changes
0
Migration Steps
1
Affected Symbols

⚠️ Check Your Code

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

ggml

Breaking Changes

Issue #1

The use of `find_library(MATH_LIBRARY m)` for linking the math library has been reverted to the standard `-lm` linking, as the former broke CUDA compilation when `GGML_STATIC` was enabled.

Release Summary

This release reverts the change to use `find_library` for math library linking in ggml back to standard `-lm` linking to resolve CUDA compilation issues when `GGML_STATIC` is enabled.

Need More Details?

View the full release notes and all changes for llama.cpp b8957.

View Full Changelog