b10354 b10353
ggml-org/llama.cppAug 10, 2026 → Aug 10, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10354 and b10353. This page updates automatically — usually within a minute.
The Two Releases
b10354
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 notesb10353
b10353
Aug 10, 2026· 2 months ago
Fixes a bug in the `ggml_roll` operation on CUDA and Metal backends. These backends were not validating tensor contiguity, leading to silent data corruption when permuted tensors were used.
Full release notes