b10369 b10362
ggml-org/llama.cppAug 12, 2026 → Aug 11, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10369 and b10362. This page updates automatically — usually within a minute.
The Two Releases
b10369
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 notesb10362
b10362
Aug 11, 2026· 2 months ago
Updated tests to skip multi-output sampling on HIP due to missing CUB support, and improved CI logging for ROCm self-hosted runners.
Full release notes