llama.cpp releasesTools
b12284
CUDA: Add OCP FP8 support ( #28413 ) Initial CUDA WIP version Use fp8 intrinsics Do W8A16 for FP8 in GEMV case (base) osimons@ub-osimons:~/lcpp_fp8.git$ ./build-x64-linux-gcc-reldbg/bin/llama-bench…
Read at llama.cpp releases ↗Related
Toolsb12285: cuda : fattn mma head sizes 40 72 (#30285) llama.cpp releases
Toolsb12263 llama.cpp releases

SiliconCongress could issue subpoena to Nvidia CEO Jensen Huang if he doesn’t respond by today to request for a ‘joint, closed-door briefing’ Tom's Hardware

SiliconCyanogen co-founder unveils Kora, a Linux OS that splits AI models across the CPU, GPU, and NPU Tom's Hardware

SiliconElon Musk wants to build a s $24 billion gas-powered AI supercomputer in Texas company town Tom's Hardware
