Satya Jandhyala#
Satya Jandhyala works on strengthening the distributed and scalable AI/ML ecosystem for AMD GPUs, enabling open‑source projects such as veRL, Ray, PyTorch, vLLM, and others across HIP and ROCm. Prior to AMD, he contributed to Microsoft’s ONNX Runtime, expanding its training and inference support to diverse backends including WebGPU, CUDA, and Snapdragon platforms for mobile and edge. Satya Jandhyala has a long track record of building high‑performance, cross‑platform systems and now focuses on enabling distributed and scalable AI/ML workloads on AMD hardware.
Posts by Satya Jandhyala
