r robertnishihara Joined 9 years ago Karma 464 Submissions 102 Member since Oct 16 View on Hacker News
High Performance Distributed Inference with Ray Serve LLM a anyscale.com 3 robertnishihara 4 months ago 0 comments
67% Cost Savings with PD Disaggregation Using Ray and vLLM on AMD MI325X a anyscale.com 4 robertnishihara 4 months ago 0 comments
Major upgrades to Ray Serve: 88% lower latency and 11.1x higher throughput a anyscale.com 2 robertnishihara 7 months ago 1 comments
SkyRL brings Tinker to your GPUs (2025) n novasky-ai.notion.site 24 robertnishihara 8 months ago 5 comments
vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep b blog.vllm.ai 147 robertnishihara 9 months ago 54 comments
Massively Parallel Agentic Simulations with Ray a anyscale.com 2 robertnishihara 1 year ago 0 comments
Deploy DeepSeek‑R1 with VLLM and Ray Serve on Kubernetes a anyscale.com 1 robertnishihara 1 year ago 0 comments
An Open Source Stack for AI Compute: Kubernetes and Ray and PyTorch and VLLM a anyscale.com 1 robertnishihara 1 year ago 0 comments
AsyncFlow: An Asynchronous Streaming RL Framework for LLM Post-Training a arxiv.org 4 robertnishihara 1 year ago 0 comments
Large-Scale Deployment of Ray in Tencent's Weixin AI Infrastructure a anyscale.com 2 robertnishihara 1 year ago 0 comments
