The open‑source LLaMA inference library adds a Vulkan fix for AMD integrated graphics and updates pre‑built binaries for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team released llama.cpp version b11461 on 2026-10-07. The update fixes a slow checkpoint read when using Vulkan on AMD integrated GPUs. It also provides new binary packages for Apple Silicon, Intel Macs, iOS, and several Linux builds (CPU, Vulkan, CUDA 12.8). Users can download the appropriate archive from the GitHub release page.
AMD laptop users can now run LLaMA models faster without the previous slowdown.
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%.
Models
Mistral's new trillion‑parameter model scores 38 on an independent index, but costs more per task than competing open models.
Models
OpenAI reported two influence campaigns that used AI‑generated content to plant false stories in real media and blocked the involved accounts.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
