search

apoorvkh / torchrunx

Launch PyTorch functions onto multiple machines & GPUs
https://torchrunx.readthedocs.io
MIT License
1 stars 0 forks source link

README and documentation #25

Open apoorvkh opened 4 months ago

apoorvkh commented 4 months ago

(for later)

apoorvkh commented 3 months ago
apoorvkh commented 2 months ago

Also include submitit example with slurm

apoorvkh commented 2 months ago

Dummy example for distributed test

https://github.com/facebookincubator/submitit/blob/07f21fa1234e34151874c00d80c345e215af4967/docs/examples/torch_distributed.py#L55-L63

Underneath that say: "could also do (e.g. DDP/FSDP) PyTorch training"