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][Experimental] feat: add Vulkan backend
- [Kernel] feat: add custom CUDA kernels for all sampling ops
- fix: illegal memory access for FP8 MoE models in cutlass 3x grouped gemm kernel
- [Kernel] feat: sage attention support
- [Kernel][Quantization] feat: add Gluon kernels for AWQ quantization
- [kernel] feat: hybrid CPU-GPU MoE inference
- 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
- Docs
- not yet supported