Journal of an ML Engineer

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT
LAWST

Home Categories llm-architecture

Category

llm-architecture 1

Different Transformers Attention Variants Jan 22, 2025

Recently Updated

PyTorch Memory Deep Dive: view, reshape, transpose, permute and the Contiguity Puzzle
Notes on PyTorch's Distributed Data Parallel (DDP)
AI Down The Line
Parameter Efficient Fine Tuning Notes
Basic_principles_distributed_training

Trending Tags

llms transformers deep-learning bert pytorch ZeRO context parallelism contiguity ddp distributed data parallel

© 2026 Rohit Singh. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

llms transformers deep-learning bert pytorch ZeRO context parallelism contiguity ddp distributed data parallel

A new version of content is available.