jaewan / jaewan/accelerator_disaggregation
add baselines
Open
- Dominant language
- Python
- Stars
- 1
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
1. BERT
2. Autoscaling
- Ray Autoscale (spawn a new VM and distribute using Ray server autoscale)
- Migrate to a bigger(or smaller) GPU
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue contains no file, test, or entry-point references, so first inspect the repository structure and existing baseline or deployment code. Clarify the intended BERT baseline and whether Ray VM autoscaling, GPU resizing, or both are required; done should be defined by reproducible baseline results and agreed autoscaling behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100