Skip to content
Blog/Ye Wang

Ye Wang

Senior Software Engineer
Ye Wang was a Senior Software Engineer at Snowflake, focusing on optimizing the inference performance of LLM systems. Previously he was also part of Microsoft's AI Framework team, where he contributed to ONNXRuntime and focused specifically on improving the performance of ONNX models on both CPU and GPU hardware.
AUG 25, 2025Gen AI

Fast Reasoning on GPT-OSS with Speculative Decoding and Arctic Inference

Jaeseong Lee +5
MAY 29, 2025Gen AI

Arctic Inference with Shift Parallelism: The Fastest Open Source Inference System for Enterprise AI

Samyam Rajbhandari
Samyam Rajbhandari +8

Where Data Does More

Start for free
Watch a demo