llama2.c VS blislab

Nice article. We did a demo for booting to LLM and also as Kernel Module: https://github.com/trholding/llama2.c The whole things was funny and buggy, but since then we have been developing in stealth, even trying to raise VC capital. Our goal is to make computers like a buddy to whom you can talk to and explain things and get work done, kinda like a Jarvis. The way we interact with computers haven't changed for decades, its time to disrupt that to get more productivity. I also believe with this approach one can avoid installing different applications, when the computer (models) emulate activities done through applications. For example, cutting and pasting a dog from a dog photo onto a banner for a dog racing competition would not require you to be a graphics artist nor use tools like photshop / gimp. You could tell the computer and it would use segment anything to cut the dog, use Text and SD for banner text and bg paste the dog, seek your approval, search for the fastest, best and cheapest banner printing service and submit it. 10 years ago this could have been sci-fi, but now it is a possibility. Just need to connect the dots, package and polish it to make it a good product.

We are trying to create a proper OS that boots to an LLM. A toy demo is available in the releases: https://github.com/trholding/llama2.c

Can we apply?

I feel you!

Here it is: https://github.com/trholding/llama2.c#new---l2e-os-linux-ker...

404? Try: https://github.com/trholding/llama2.c

Efficient matrix multiplications or convolutions on CPU will use layered tiling to optimize registers, L1, L2 and TLB, L3 cache (if it exist). This improve speed by over 150x vs naive triple for-loop matrix multiplication and the same thing applies to convolution. See overview https://www.cs.utexas.edu/users/flame/laff/pfhp/week3-goto.html and actual exercises https://github.com/flame/blislab