Coding Tools
llama.cpp b11331 adds NVFP4 and CUDA 13 support
llama.cpp Releaseshigh confidence
Why it matters
- →Enables efficient inference on newer NVIDIA hardware using NVFP4 quantization.
- →Ensures compatibility with the latest CUDA 13 drivers and libraries.
- →Improves stability for MoE models by preserving operator parameters during execution.
llama.cpp has released version b11331, introducing support for NVFP4 quantization and CUDA 13. The update includes specific fixes for compute types in the cuBLAS path to ensure BF16 precision is maintained during inference with NVFP4 models. Additionally, pre-built binaries are now available for CUDA 13.4 across Linux and Windows platforms. This release also preserves operator parameters for per-expert matrix multiplications, improving stability for Mixture of Experts (MoE) architectures.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Llama.cpp b10099 Release Enhances CUDA Quantization
llama.cpp Releases · July 25, 2026 · Same story
- 2llama.cpp b10900 Release Expands Platform Support
llama.cpp Releases · September 11, 2026 · Same story
Follow this story
Open the full story →llama.cpp b11052 adds CUDA 13 and ROCm 10 builds
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.323 adds experimental Code Mode and plugin safety
This release quietly introduces Code Mode, an opt-in feature where Claude writes JavaScript to call its own tools, marking a shift toward more autonomous agent-like behavior within the CLI. The update also hardens the plugin ecosystem by enforcing version ranges and adding strict TypeScript type checking for hooks, which should significantly reduce instability from third-party extensions. Beyond these features, the changelog is dominated by critical fixes for authentication drift in background sessions and memory leaks when handling large files, stabilizing the tool for heavy enterprise use.
Claude Code Releases
© GitHub ChangelogCoding Toolscoding