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
- [Kernel][Quantization] feat: add Gluon kernels for AWQ quantization
- [Feature]: Support for Triton attention backend for inference
- [kernel] feat: hybrid CPU-GPU MoE inference
- [Feature]: enablement of XPU features from intel/llm-scaler's vllm/patches
- Fix metrics and allow disable block manager v2
- [Bug]: YAML run option no longer available in 0.9.0
- [kernel][moe] better splitK for fused moe
- feat(compilation): Extend sequence parallelism to activations
- Allow to force p2p
- feat: overlap shared experts with send/recv
- Docs
- not yet supported