SpecForge
SpecForge copied to clipboard
[Feature] VLM model support flex attention
Checklist
- [ ] 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/SpecForge/discussions/new/choose Otherwise, it will be closed.
- [ ] 2. Please use English, otherwise it will be closed.
Motivation
VLM model support flex attention
Related resources
No response