Lightning-AI / Lightning-AI/litgpt
serving with multi-GPU
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 13.7k
- Forks
- 1.5k
- Avg merge
- 15h 37m
- Merged PRs (30d)
- 1
Description
I was testing "litgpt serve" for llama-3-70b using 4 A100 80G and I receive OOM error. I tried the same command on llama-2-13b and it seems like specifying the "devices" argument only load multiple replicas of the same model but not distributing the memory. Is there any way to do multi-gpu serving with the model?
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 at the `litgpt serve` entry point and trace how the `devices` argument is handled for the llama-3-70b and llama-2-13b cases. Determine whether serving distributes one model across GPUs or only creates replicas; done means the supported behavior and any required change are clearly established.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, distributed-systems
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100