deepspeedai / deepspeedai/DeepSpeed
[REQUEST] Dynamic model offload support ZeRO-3 inference models
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
Is your feature request related to a problem? Please describe.
The issue is related to #5620 and #6011. When having a deespeed model initialised for ZeRO-3 inference, with a DeepSpeedZeRoOffload optimizer for example, the model cannot be moved to the CPU either by using the torch.nn.module.to() functionality or with the new offload_states API.
Describe the solution you'd like
Either extend #6011 to support offload of a model configured for ZeRO-3 inference or a new API that supports this.
Thanks
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the linked issues #5620 and #6011, then inspect deepspeed/runtime/zero/parameter_offload.py and the DeepSpeedZeRoOffload optimizer. Compare torch.nn.Module.to() with the offload_states API for ZeRO-3 inference models. Done means a ZeRO-3 inference model can be offloaded to CPU through an extended API or a new API.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- distributed-systems, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100