llama.cpp releasesTools
b12342
Title: CUDA: few-row MMQ for BS 2-24 ( #31533 ) CUDA: few-row MMQ for 2-24 src1 columns New int8 MMA kernel for quantized mat-muls with 2-24 src1 columns, e.g. speculative decoding verify passes.
Read at llama.cpp releases ↗Related

AsiaJensen Huang quits Nvidia; non-invasive treatment for kidney tumours: SCMP’s 7 highlights SCMP Tech

Jensen Huang’s scandal-fueled ouster exposes enterprise doubts about AI AI Business

VoicesSharp Tech on Video: Nvidia After Jensen Huang, Ominous News for American AI, D.C. Gets Its Revenge Stratechery
AsiaHiSilicon CS6286 Image Sensor Puts AI On-Chip, Stretching Dashcam Sentry Mode Past Seven Days Pandaily

AsiaOla Electric Slides In Q2, NVIDIA CEO Quits & More Inc42
