# llama.cpp release adds CUDA ssm_conv kernel size 7

> The ggml-org/llama.cpp v b11770 adds a new CUDA kernel for SSM convolution and provides fresh binaries for macOS, iOS and Linux.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-adds-cuda-ssm-conv-kernel-size-7

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.

## The facts

- Release version: b11770
- Release date: Wed Oct 21 2026

## Why it matters

Developers can run larger SSM‑based models faster on Nvidia GPUs thanks to the new kernel.

## Sources & references

1. [ggml-org/llama.cpp b11770](https://github.com/ggml-org/llama.cpp/releases/tag/b11770) – llama.cpp, 2026-10-21

Last updated: 2026-10-21