Models & Labs
Llama.cpp b10330 Release Enhances CUDA Performance
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances CUDA performance by fusing key operations, improving efficiency.
- →Supports a wide range of systems, making it versatile for developers.
- →Strengthens llama.cpp's position as a reliable inference runtime.
Llama.cpp has released its b10330 update, which enhances CUDA performance by fusing operations such as rms_norm, mul, and rope. This release includes checks on memory ranges before fusion, aiming to optimize efficiency on CUDA platforms. The update supports a wide range of systems, including macOS, Linux, and Windows, but does not introduce new models. This makes llama.cpp a more efficient inference runtime, particularly benefiting developers using NVIDIA GPUs with CUDA 12 and 13.
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 b10164 Release Enhances CUDA Performance
llama.cpp Releases · July 29, 2026 · Same story
What happened next
- 2Llama.cpp b10751 Release Enhances CUDA Efficiency
llama.cpp Releases · September 2, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
