b10355 b10354
ggml-org/llama.cppAug 10, 2026 → Aug 10, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10355 and b10354. This page updates automatically — usually within a minute.
The Two Releases
b10355
b10355
Aug 10, 2026· 2 months ago
Implements support for multi-output backend sampling, allowing the sampling process to be performed on the backend (GPU/CPU) to enable token speculation and improve performance.
Full release notesb10354
b10354
Aug 10, 2026· 2 months ago
Fixes a bug where CPU affinity masks were being ignored on Android, which could lead to incorrect thread scheduling or performance issues on Android devices.
Full release notes