Back to Freedom.Tech Back
All llama.cpp releasesAll versions
Release Tue, Sep 8, 2026 1 min read

llama.cpp b10864

Original release notes

server : apply checkpoint min-step eviction only when the checkpoint list is full (#28302)

The spacing eviction in create_checkpoint() keeps the oldest checkpoint and erases every later one within checkpoint_min_step of it. For prompts shorter than checkpoint_min_step this drops the checkpoint at n_tokens - 4 that the next request resumes from, so hybrid/recurrent models re-prefill from the previous checkpoint instead. Apply the spacing rule only once the list is at n_ctx_checkpoints, and replace an existing checkpoint at the same n_tokens instead of appending a duplicate.

Website: -

Attestations: -

UI: