News for hackers. Stuff that matters.
Re:Llm.c – LLM training in simple, pure C/CUDA by andy99 on Monday April 08, 2024 @06:07PM (#39974235)
I'd like to think he took the name from my llm.f90 project https://github.com/rbitr/llm.f90

It was originally based off of Karpathy's llama2.c but I renamed it when I added support for other architectures.

Probable a coincidence :)

Re:Llm.c – LLM training in simple, pure C/CUDA by matteogrella on Tuesday April 09, 2024 @04:14AM (#39977181)
I'm the creator behind https://github.com/nlpodyssey/rwkv.f90. How about joining forces?
Re:Llm.c – LLM training in simple, pure C/CUDA by andy99 on Tuesday April 09, 2024 @09:51AM (#39979439)
I'll send you an email
Re:Llm.c – LLM training in simple, pure C/CUDA by bee_rider on Tuesday April 09, 2024 @11:28AM (#39980505)
In f90? That’s pretty cool.

On a related note, IMO it would be pretty cool if we could get an LLM implementation that provides and RCI interface like all the old computational codes used to.