CUDA: compress mode option and default to size (llama/12029)

CUDA: app option to compile without FlashAttention (llama/12025)

CUDA: correct the lowest Maxwell supported by CUDA 12 (llama/11984)

cuda : add ampere to the list of default architectures (llama/11870)

CUDA: use mma PTX instructions for FlashAttention (llama/11583)

ggml : sync remnants (skip) (#0)

ggml : sync resolve (skip) (#0)