Evangelos Georganas

This is the file that generates the opreduce tests: https://github.com/libxsmm/libxsmm/blob/main/samples/eltwise/kernel_test/create_new_opreduce_simple_test.sh

You'd have to enhance the scripts... All I was trying to say is that the various opreduce tests were generated by another script and this shall be the method for...

DOT and GEMV are BW BOUND ops, so AMX is irrelevant On Mon, Aug 14, 2023 at 10:24 AM Hans Pabst ***@***.***> wrote: > General Q (raised by others), this...

Well, then one is better off by reformulating the algorithm/math to use matmul. This is a standard trick in linear algebra… On Mon, Aug 14, 2023 at 11:00 AM Hans...

Closed by PR #868

The main reason is the resources that would be required for the actual pruning of the largest Llama2-70b model... is it a modern GPU with large memory? Or a DGX...

Thanks a lot, please let me know when/if you are able to release the LLaMA-2-70b models.