Hey there!
I’m Niyar, an M2 student at Université de Toulouse working on NLP, LLM reasoning, and mechanistic interpretability. Sometimes I write CUDA kernels and pretend I know what I’m doing.
This is where I think out loud. A public notebook of sorts: half-baked ideas, research notes, and the occasional breakthrough. Mostly for future me, but you’re welcome to stick around.
Recent Posts
-
● pinned
CUDA Learning Log
figuring out GPUs, one kernel at a time.