The ggml‑org/llama.cpp project released version b11469 on Oct 7, 2026, featuring a MUSA tile‑lightning indexer kernel and pre‑built binaries for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
ggml‑org released llama.cpp version b11469. The update adds a MUSA tile‑lightning indexer kernel, contributed by Xiaodong Ye. It also ships ready‑to‑run binaries for Apple Silicon, Intel Macs, iOS, and several Ubuntu builds (CPU, Vulkan and CUDA). Users can download the appropriate package from the GitHub release page.
Developers can now run llama.cpp locally on more hardware, including MUSA‑compatible GPUs, 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.
