High Performance Distributed Inference with Ray Serve LLManyscale.com3 points·by robertnishihara·há 24 dias·0 comments
Data Processing Is Becoming a GPU Workloadanyscale.com2 points·by robertnishihara·há 26 dias·0 comments
67% Cost Savings with PD Disaggregation Using Ray and vLLM on AMD MI325Xanyscale.com4 points·by robertnishihara·há 26 dias·0 comments
Major upgrades to Ray Serve: 88% lower latency and 11.1x higher throughputanyscale.com2 points·by robertnishihara·há 4 meses·1 comments
SkyRL brings Tinker to your GPUs (2025)novasky-ai.notion.site24 points·by robertnishihara·há 5 meses·5 comments
vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-epblog.vllm.ai147 points·by robertnishihara·há 6 meses·54 comments
Massively Parallel Agentic Simulations with Rayanyscale.com2 points·by robertnishihara·há 10 meses·0 comments