b10541 b10539
ggml-org/llama.cppAug 21, 2026 → Aug 21, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10541 and b10539. This page updates automatically — usually within a minute.
The Two Releases
b10541
b10541
Aug 21, 2026· 2 months ago
Adds a command-line argument `--mmproj-device` to the MTMD (Multi-Modal Text-to-Model) backend to allow specifying the device for the multimodal projection model.
Full release notesb10539
b10539
Aug 21, 2026· 2 months ago
Fixes a potential overflow in the Vulkan Flash Attention (FA) MMQ kernel where Q quantization calculations used denormalized floats.
Full release notes