Open Source
llama.cpp b10992 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform compatibility, making it more versatile for developers.
- →Supports both AMD and NVIDIA users, broadening its appeal.
- →Enhances accessibility for AI practitioners across diverse hardware configurations.
The b10992 release of llama.cpp has been announced, featuring expanded support for various platforms. This update includes compatibility with Ubuntu systems using Vulkan and CUDA 13.3 libraries, as well as Windows systems with OpenCL Adreno. The release also supports ROCm 10.0, making it more accessible for AMD users. Although no new model architectures are included, the update enhances the tool's versatility across different hardware setups, reinforcing its role as a comprehensive inference runtime.
Read originalMore from llama.cpp Releases
Coding Toolscoding
llama.cpp b10993 adds ROCm 10 and CUDA 13 builds
This release quietly extends llama.cpp's hardware support to the latest driver stacks, adding official binaries for ROCm 10.0 and CUDA 13 across Linux and Windows. For AMD users, this means native compatibility with newer GPU architectures without manual compilation tweaks, while NVIDIA users gain access to the latest CUDA runtime optimizations. The inclusion of WebGPU in CI signals ongoing work toward browser-based inference, though it remains a background effort for now. There are no new model formats or quantization methods here, just broader infrastructure coverage that keeps llama.cpp relevant as hardware evolves.
llama.cpp Releases
Coding Toolscoding
llama.cpp fixes Metal NaN bug for large activations
A critical precision bug in llama.cpp’s Apple Silicon backend has been patched, resolving total inference failures on models with high-activation ranges like Mistral Small 4. The issue stemmed from f16 saturation during matrix multiplication, which turned entire output tensors into NaN values for inputs exceeding ~32 tokens. By implementing an exact, power-of-two rescaling mechanism in the Metal kernel, the fix restores correctness without significant performance penalties. This ensures local inference on M-series chips remains viable for complex MoE architectures that previously crashed.
