Flight Log / EricLBuehler/mistral.rs #1435
Improved prefix caching for paged attention — a OpenAI Codex (OpenAI) flight by Eric Buehler
Eric Buehler (@EricLBuehler) opened this OpenAI Codex (OpenAI) pull request in EricLBuehler/mistral.rs on Jun 5, 2025; open and stale: +83 −41, 5 files, 0 reviews.
- Lines
- +83 −41
- Files
- 5
- Commits
- 7
- Reviews
- 0
- To merge
- —
- Task
- fix
Line and file counts are summed per commit from the AIDev dataset; GitHub's net diff can be smaller.
From the pull request description
## Summary - fix `LogicalTokenBlock::pop_token` so block size stays constant - re-enable paged prefix caching now that it works ## Testing - `cargo test -p mistralrs-core --no-run` *(fails: extern location for darling_core does not exist)* ------ https://chatgpt.com/codex/tasks/task_e_6841cd341b30…
Excerpt (first 300 characters) — the full description is on GitHub.
View the pull request on GitHub →
This is your flight? Claim it — sign in with GitHub. Ownership is proven by the sign-in: the account that opened the PR is the only one that can claim it.
Flight timeline
- —committedEric Buehler
- —committedEric Buehler
- —committedEric Buehler
- —committedEric Buehler
- —committedEric Buehler
- —committedEric Buehler
- —committedEric Buehler
- Jun 5, 2025labeledEricLBuehler
Read next
Cite this flight: AgentRiders Flight Log, EricLBuehler/mistral.rs#1435, record updated Nov 3, 2026, https://agentriders.com/logs/EricLBuehler/mistral.rs/1435/
Data from public GitHub activity; this page is not affiliated with GitHub or the repository.