Distributed communication for GPUs (part 1)
Introduction to distributed communication for GPUs.
Ultra-Scale Playbook
Choosing a batch size and provider for LLM training
Notes on choosing appropriate batch size and compute for training LLMs
Ultra-scale Playbook - Deepspeed ZeRO
Notes on training LLMs using sharding strategies
Ultra-scale Playbook - Data Parallelism
Notes on training LLMs using data parallelism strategy
Ultra-scale Playbook - Train on a single GPU
Notes on Ultra-scale Playbook - training LLM on a single GPU