-
Aug 15, 2024
Qunatizing the Large Language Model - GPTO
Notes on Quantizations of DNN | Pre-req for GPTQ -
Aug 14, 2024
Optimal Brain Quantizer - Pruning and Quantizing the Neural Nets
Notes on Quantizations of DNN | Pre-req for GPTQ -
Jul 13, 2024
Training Models Across Multiple Machines - The Federated Learning Way
Notes on Distributed Training -
Jun 7, 2024
How to train your Cuda? Going deep to GPU Architecture!
The overall Architecture of the GPU and some bottlenecks! -
May 13, 2024
Eveything Everywhere at once - A Distributed Training Saga...
my notes on distributed data parallelism(DDP) -
Apr 1, 2024
2.0 - Language Models as Operating System
This is my notes exploring the usecase of Large Language Models as an Operating System of this decade. P -
Jan 7, 2024
How to Program Your GPUs? Learning Cuda...
how to operate the parallel chips if i ever become GPU rich... -
Jan 7, 2024
State Space Models - Discretization and Convolution
Notes on States Space Model and Mamba Architecture