Kawrakow e787c00141 Reduce size of compute buffers (#237) ... * This reduces compute buffer size for MLA * This should accomplish it for standard attention * Much better * Better concat for contiguous tensors If all the op does is to concatenate the second tensor to the first, why would we want to have a loop? --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>		2025-03-01 08:25:27 +02:00
..
llama.h	Reduce size of compute buffers (#237)	2025-03-01 08:25:27 +02:00