The open‑source Llama.cpp library released version b11501 on Oct 8 2026, bringing SYCL fast Walsh‑Hadamard transform tweaks and pre‑built binaries for macOS, iOS and several Ubuntu GPU setups.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team published llama.cpp version b11501 on Oct 8 2026. The update adds SYCL (a cross‑platform compute API) fast Walsh‑Hadamard transform optimizations, which can speed up certain matrix ops. It also ships ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and Ubuntu builds with CPU, Vulkan and CUDA 12.8 support.
Developers can now run Llama models faster on SYCL‑compatible GPUs and avoid building the library themselves.
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.
