deepspeedai / deepspeedai/DeepSpeed
checkpoint type error
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
Try to figure out a way to run deepspeed inference following the tutorial, but run into error:
assert False, '{} checkpoint type is not supported'.format(sd_type)
AssertionError: DeepSpeed checkpoint type is not supported
The error came from the initialization:
ds_engine = deepspeed.init_inference(dalle,
checkpoint="./checkpoint.json")
checkpoint.json:
{
"type": "DeepSpeed",
"version": 0.3,
"checkpoints": "./ckpt/epoch5.pt"
}
Any suggestion on this issue? Or a sample code to set inference up would be appreciated.
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 by reproducing the tutorial's deepspeed.init_inference call with checkpoint.json and ./ckpt/epoch5.pt, then inspect where the checkpoint type is validated. Compare the JSON structure with the inference setup described in the tutorial. Done means identifying whether this checkpoint format is supported and documenting a reproducible working setup or the required correction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100