b10538 b10537
ggml-org/llama.cppAug 21, 2026 → Aug 21, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10538 and b10537. This page updates automatically — usually within a minute.
The Two Releases
b10538
b10538
Aug 21, 2026· 2 months ago
Optimizes the macOS Metal backend by dequantizing the Key-Value (KV) cache only for large batches to reduce overhead and improve efficiency.
Full release notesb10537
b10537
Aug 21, 2026· 2 months ago
Updates the CI build process to use LLVM's OpenMP library instead of the Microsoft debug version, improving compatibility and packaging.
Full release notes