robertnishihara

Recent Submissions

1. 1. ▲ vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep (blog.vllm.ai) 147 points · 22 days ago · 54 comments
2. 2. ▲ Massively Parallel Agentic Simulations with Ray (anyscale.com) 2 points · 4 months ago · 0 comments
3. 3. ▲ Deploy DeepSeek‑R1 with VLLM and Ray Serve on Kubernetes (anyscale.com) 1 point · 5 months ago · 0 comments
4. 4. ▲ An Open Source Stack for AI Compute: Kubernetes and Ray and PyTorch and VLLM (anyscale.com) 1 point · 6 months ago · 0 comments
5. 5. ▲ Native LLM APIs in Ray Data and Ray Serve (anyscale.com) 2 points · 7 months ago · 0 comments
6. 6. ▲ Joins and Hash-Shuffle in Ray Data (anyscale.com) 3 points · 7 months ago · 0 comments
7. 7. ▲ AsyncFlow: An Asynchronous Streaming RL Framework for LLM Post-Training (arxiv.org) 4 points · 7 months ago · 0 comments
8. 8. ▲ Open Source RL Libraries for LLMs (anyscale.com) 1 point · 7 months ago · 0 comments
9. 9. ▲ Large-Scale Deployment of Ray in Tencent's Weixin AI Infrastructure (anyscale.com) 2 points · 7 months ago · 0 comments
10. 10. ▲ Uv and Ray: Pain-Free Python Dependencies in Clusters (anyscale.com) 44 points · 7 months ago · 10 comments