deepspeedai / deepspeedai/DeepSpeed
[REQUEST] Is there any demo or tutorial for Deepspeed pipeline inference?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
Hi! I am a graduate student who have read the paper about the Deepspeed framework.https://arxiv.org/pdf/2207.00032 I gain great interests on the hybrid pipline inference strategy descrided in Section Ⅳ, but when learn how to implement it in offical tutorial website, I found there are only some parts teaching how to us PP for training instead of inferencing. So I wonder if there are someone who know where the pipeline inference turorial is or have the experience for hybrid pipeline inference strategy?
Sry I am not an English native speaker, my writing is poor. :(
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 reviewing the official DeepSpeed tutorial website and Section IV of the linked paper to determine what pipeline inference guidance already exists. Done would mean providing a concrete demo or tutorial for the hybrid pipeline inference strategy, but the issue does not identify a file, test, or documentation entry point.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100