Coding Tools

llama.cpp b11022 adds CUDA 13 and ROCm 10 support

llama.cpp ReleasesSeptember 18, 2026high confidence

Why it matters

→CUDA 13 support allows users to leverage the latest NVIDIA GPU architectures without custom compilation.
→ROCm 10.0 integration improves performance and compatibility for AMD GPU users running local models.
→openEuler builds provide official support for Huawei Ascend AI accelerators, expanding hardware options.

llama.cpp has released version b11022, updating its pre-built binaries to support CUDA 13 and ROCm 10.0 on Linux and Windows platforms. The update also includes builds for openEuler targeting Huawei Ascend hardware (910b) and maintains standard CPU, Vulkan, and OpenVINO options. Notably, KleidiAI optimization is disabled for macOS Apple Silicon binaries in this release. The update ensures compatibility with the latest NVIDIA and AMD driver stacks for local LLM inference.

Read original

llama.cpp b11022 adds CUDA 13 and ROCm 10 support

Why it matters

More from llama.cpp Releases

llama.cpp b11017 adds CUDA 13 and ROCm 10 builds

llama.cpp b11018 adds CUDA 13 and ROCm 10 builds

More in Coding Tools

Claude Code v2.1.275 patches stability and sync

Claude Code v2.1.276 fixes proxy regression

llama.cpp b11019 fixes embedded GGUF loading bugs

GitHub Copilot adds feature-level engagement metrics