CUDA: mul_mat_id for mmf for bs <= 64 for f16 and bs <= 32 for f32#16277

JohannesGaessler merged 2 commits intoggml-org:masterggml-org/llama.cpp:masterfrom

am17an:cuda_mmf_mmidam17an/llama.cpp:cuda_mmf_mmidCopy head branch name to clipboard