b10330 b10329
ggml-org/llama.cppAug 8, 2026 → Aug 8, 20260 days between releases
Generating AI comparison
Analyzing what changed between b10330 and b10329. This page updates automatically — usually within a minute.
The Two Releases
b10330
b10330
Aug 8, 2026· 2 months ago
Optimizes CUDA performance by fusing RMS normalization, multiplication, and RoPE operations into a single kernel launch.
Full release notesb10329
b10329
Aug 8, 2026· 2 months ago
Updates the Server and UI to only display the working directory control when at least one enabled tool actually requires it.
Full release notes