Distributed LLM Pretraining Torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

photonics-dhl Updated 0 repo stars

File contents

photonics-dhl/scholar-s-tea commit 28f0f39f8e

Frequently asked questions

npx get-skill add photonics-dhl/distributed-llm-pretraining-torchtitan