The ggml‑org/llama.cpp project posted version b11325 on Oct 1 2026, adding updated binaries for macOS, iOS and several Linux builds.
NoteOossaPublished by Oossa: 1 min read
The open‑source llama.cpp library released version b11325 on Oct 1 2026. It adds fresh pre‑built binaries for Apple Silicon Macs, Intel Macs, iOS, and multiple Linux targets, including CPU, Vulkan and CUDA variants. The release also includes a small code tweak for the Jinja templating system.
Developers can now download ready‑to‑run llama.cpp binaries for more platforms without building from source.
Last updated: ·Markdown
Models
Google’s new Guided Vision feature launches on Android phones, giving audio descriptions of what the camera sees, aimed at users with low vision.
Models
In a test, nearly half of participants thought the new AI video avatar was a real person, far above earlier systems.
Models
The companies will build GPT-Synopsys to operate Synopsys design tools. Early customer engagements are underway, but a general release date is not given.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
