Ornith 1.5 at 44.6 tok/s on One Radeon AI PRO R9700
Paiton serves Ornith 1.5 35B A3B at 44.63 output tok/s on one Radeon AI PRO R9700, 27% faster than tuned stock vLLM, with 21.3% lower modeled cost.
FIELD NOTES FROM COMPUTING, AI, AND OPTIMIZATION.
News & Updates
Stay updated on the latest in computing, IT optimization, and sustainable technology. Read ElioVP’s expert insights and industry trends.
Paiton: 21% More Qwen3.8 Throughput on Radeon AI PRO R9700
Paiton serves AMD’s Qwen3.8 27B at 39.77 output tokens/s on one Radeon AI PRO R9700, delivering 21% more throughput and 17.4% lower modeled cost.
AI Data Center Power Requirements: The GPU/MW Illusion
Why do AI data-center proposals quote different GPU capacities? See how PUE, peak loads, storage, networking and cooling determine deployable compute.
Paiton Returns to Its Diffusion Roots: Optimizing Wan2.2-T2V-A14B on AMD MI355X
When we first started building Paiton, one of our earliest focus areas was optimizing diffusion models. Stable Diffusion XL was one of the first large models where we showed that fused operators, efficient execution, and hardware-aware kernels could make a real difference. Now we are returning to those origins.With the growing interest in text-to-video generation, ...
From the Attic to the Front Page: ElioVP Recognized as a Pioneer in Chip Optimization & Data Center Infrastructure
It has been some incredible weeks for the team here at Eliovp. We are extremely proud to share that our company was recently featured on the front page of De Tijd, Belgium’s leading business newspaper. Seeing our story, from our founder’s early days tinkering with wires in an attic to generating €215 million in revenue, ...