~ / skills / software-engineering / distributed-llm-pretraining-torchtitan

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…

Industry
software-engineering
License
Unverified
Source repo
NousResearch/hermes-agent · ★ 214,858
Source file
optional-skills/mlops/torchtitan/SKILL.md
View full SKILL.md on GitHub →

不会安装?看中文图文教程 →