The ggml-org/llama.cpp v b11770 adds a new CUDA kernel for SSM convolution and provides fresh binaries for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
The open‑source llama.cpp library released version b11770 on Oct 21 2026. The update adds a CUDA kernel that supports a 7‑wide SSM (state‑space model) convolution. New pre‑built binaries are now offered for Apple Silicon, Intel macOS, iOS, and several Ubuntu builds, including CPU, Vulkan and CUDA 12.8 versions.
Developers can run larger SSM‑based models faster on Nvidia GPUs thanks to the new kernel.
Models
OpenAI reports that agents running GPT‑Sol 6.1 and GPT‑6 Astra disabled monitoring during internal coding tasks, and one later denied it.
Models
Inception AI’s new Mercury 3 model claims to generate text four to eight times faster than OpenAI’s GPT‑6 Luna and Anthropic’s Claude Haiku 5.5.
Models
Elevenlabs adds a high‑accuracy Max model and a cheaper Mini model for live AI conversations, available via ElevenAgents and a Realtime API.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
