The open‑source Llama inference library updates to b11555, fixing AVX2 CPUs that missed F16C support and publishing fresh builds for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
ggml‑org released llama.cpp version b11555. The update corrects a bug where AVX2 CPUs did not use the F16C instruction set even when it was available. The release also ships new binary packages for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu configurations including Vulkan and CUDA 12.8 support.
Developers running Llama models on compatible CPUs will see faster inference without manual patches.
Models
Vals AI’s study shows multi‑agent setups can spend up to five times the tokens of a single model for only tiny quality gains.
Models
Odyssey’s Odyssey‑3 model can now generate and run 3‑D worlds from text prompts, with a free online demo and API sign‑ups.
Models
The company’s new three‑agent Claude‑based reviewer found 73.43% of core‑claim errors, far above the previous best of 14.81%.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
