Distributed Training skills
Free agent skills tagged distributed training, ready to install into any SKILL.md-compatible agent.
6 skills
Multi-Node Slurm
nvidia
Easily convert single-node scripts to multi-node Slurm jobs.
Developer ToolsintermediatePython · Shell2.8k repo
HuggingFace Accelerate
nousresearch
Simplify distributed PyTorch training with minimal code changes.
Developer ToolsintermediatePython · Shell228.5k repo
Megatron FSDP
nvidia
Optimize distributed training with Megatron FSDP.
Developer ToolsintermediatePython · Shell2.8k repo
Ray Train
orchestra-research
Effortlessly scale your ML training across clusters.
Developer ToolsintermediatePython · Shell11.6k repo
TorchTitan
davila7
Efficient distributed LLM pretraining with PyTorch.
Developer ToolsadvancedPython · Shell30.2k repo
HuggingFace Accelerate
davila7
Simplify distributed training with minimal code changes.
Developer ToolsintermediatePython · Shell30.2k repo