Priyam Mazumdar (@data_adventurer) 's Twitter Profile
Priyam Mazumdar

@data_adventurer

Our eyes let us see the universe, AI may let us finally understand it! | PhD @ UIUC | Researcher @ NCSA AI Innovation | R&D Intern @ Sandia | Avid Photographer

ID: 1828057343885529088

linkhttps://www.priyammazumdar.com/ calendar_today26-08-2024 13:10:28

175 Tweet

38 Followers

39 Following

Priyam Mazumdar (@data_adventurer) 's Twitter Profile Photo

Does any one else use coil whine for confirmation that something is actually happening?? I can’t tell if my gpus are talking or screaming in pain

Priyam Mazumdar (@data_adventurer) 's Twitter Profile Photo

Also, Liger Kernels, y'all are incredible for open sourcing so many of these triton kernels! It has been an incredible learning tool! github.com/linkedin/Liger…

Priyam Mazumdar (@data_adventurer) 's Twitter Profile Photo

writing a distributed dataloader that can also save and resume training sucked... the more I build mytorch the more I appreciate the awesome people who made PyTorch!!

Priyam Mazumdar (@data_adventurer) 's Twitter Profile Photo

Have a few test runs going on a 560M Param model using only MyTorch! Having some stability issues im sorting through but this lo key might actually work!

Priyam Mazumdar (@data_adventurer) 's Twitter Profile Photo

Policy Gradients are an extremely important idea that allows us to avoid doing a two step approach of first estimating Q values and then deriving the Policy from there. The main trick is how can we describe the derivative of our policy! Today we do that derivation and then a