b10373 b10369
ggml-org/llama.cppAug 12, 2026 → Aug 12, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10373 and b10369. This page updates automatically — usually within a minute.
The Two Releases
b10373
b10373
Aug 12, 2026· 2 months ago
Optimized imatrix calculation by moving finite checks and limiting validation to only the experts that were touched during the run.
Full release notesb10369
b10369
Aug 12, 2026· 2 months ago
Added support for Pocket-TTS in Multi-Modal models, optimizing convolution operations to reduce generation latency significantly.
Full release notes