aphrodite-engine
https://github.com/pygmalionai/aphrodite-engine
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
not yet supported1 Subscribers
Add a CodeTriage badge to aphrodite-engine
Help out
- Issues
- [Usage]: Please provide the environment variable that closes the KoboldAI Lite page.
- [Feature]: An alternative to `max_tokens` which defaults to `minimum(max_tokens, remaining_tokens)`
- [Feature]: BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences
- [Feature]: Exllamav2 Q4, Q6, and Q8 cache
- Classifier-Free Guidance support
- feat: typical_p threshold sampling
- [sparsetral and Qwen2idae]: support for mixtral of lora
- Docs
- not yet supported