robertnishihara

Recent Submissions

1. 1. ▲ High Performance Distributed Inference with Ray Serve LLM (anyscale.com) 3 points · 17 days ago · 0 comments
2. 2. ▲ Data Processing Is Becoming a GPU Workload (anyscale.com) 2 points · 19 days ago · 0 comments
3. 3. ▲ 67% Cost Savings with PD Disaggregation Using Ray and vLLM on AMD MI325X (anyscale.com) 4 points · 20 days ago · 0 comments
4. 4. ▲ Major upgrades to Ray Serve: 88% lower latency and 11.1x higher throughput (anyscale.com) 2 points · 3 months ago · 1 comment
5. 5. ▲ SkyRL brings Tinker to your GPUs (2025) (novasky-ai.notion.site) 24 points · 4 months ago · 5 comments
6. 6. ▲ vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep (blog.vllm.ai) 147 points · 5 months ago · 54 comments
7. 7. ▲ Massively Parallel Agentic Simulations with Ray (anyscale.com) 2 points · 9 months ago · 0 comments
8. 8. ▲ Deploy DeepSeek‑R1 with VLLM and Ray Serve on Kubernetes (anyscale.com) 1 point · 10 months ago · 0 comments
9. 9. ▲ An Open Source Stack for AI Compute: Kubernetes and Ray and PyTorch and VLLM (anyscale.com) 1 point · 11 months ago · 0 comments
10. 10. ▲ Native LLM APIs in Ray Data and Ray Serve (anyscale.com) 2 points · 12 months ago · 0 comments