Yifan Qiao issues

Repositories
Issues
Comments

Results 3 issues of


                                            Yifan Qiao

Where can I find traces and configs to reproduce results in the original OSDI paper?

Dear author, Thank you for open-sourcing the amazing system. I am interested in running it and reproducing the results in your OSDI RobinHood paper, but it seems I cannot find...

[RFC] Support multiple attention types

## Motivation Emerging models are increasingly adopting a hybrid of multiple attention types to capture different aspects of the input data. For example, GPT-oss uses a combination of full attention...

enhancement

📈 Roadmap

## 🎯 Q2 2025 - [X] Command line tools to check/configure physical memory usage/limit of each running instance - [X] Support Tensor parallelism - [X] Performance optimizations for physical memory...