Skip to main content
← Back to news

llama.cpp b12122: NVFP4 gate/up matmuls and GLU fused in MMQ on CUDA, one kernel for the quantized MLP block

Tools & releases
Source:GitHub
llama.cpp b12122 fuses NVFP4 gate/up matmuls and GLU in MMQ on CUDA: one kernel for the quantized MLP block, honoring the requested src1 precision and sharing scale checks. The release ships builds for CUDA 12 and 13, ROCm, Vulkan, SYCL and Snapdragon.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.