The open‑source llama.cpp library updates SYCL support and releases pre‑built binaries for macOS, iOS and Ubuntu.
NoteBy OossaPublished by Oossa: 1 min read
The llama.cpp project released version b11497 on Oct 8, 2026. It adds a SYCL optimization that fuses add, unary and multiply operations in the delta‑net alpha gate. The update also adds test coverage for this fused chain. Pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu builds (CPU and Vulkan) are now available for download.
Developers can run llama.cpp faster on more hardware without building from source.
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.
