Phani Vaddadi

Phani Vaddadi is a Principal Member of Technical Staff at AMD. He is passionate about advancing AI especially in the generative models and knowledge graphs and accelerating them on hardware. He has over three decades of experience in building products, integrating latest research into these products, creating significant value large customers across several industries.

Posts by Phani Vaddadi

Accelerating Parallel Programming in Python with Taichi Lang on AMD GPUs

This blog provides a how-to guide on installing and programming with Taichi Lang on AMD Instinct GPUs.

July 31, 2025 by Tiffany Mintz, Yao Liu, Phani Vaddadi, Vish Vadlamani

Graph Neural Networks at Scale: DGL with ROCm on AMD Hardware

Accelerate Graph Deep Learning on AMD GPUs with DGL and ROCm—scale efficiently with open tools and optimized performance.

July 31, 2025 by Mukhil Azhagan Mallaiyan Sathiaseelan, Anuya Welling, Yao Liu, Phani Vaddadi, Vish Vadlamani

Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration

Deploy verl on AMD GPUs for fast, scalable RLHF training with ROCm optimization, Docker scripts, and impressive throughput-convergence results

April 24, 2025 by Yusheng Su, Vicky Tsang, Yao Liu, Phani Vaddadi, Vish Vadlamani, Zicheng Liu

Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs

Learn how to use Megablocks to pre-train GPT2 Mixture of Experts (MoE) model, helping you scale your deep learning models effectiveness on AMD GPUs using ROCm

March 23, 2025 by Fabricio Flores, Rishi Madduri, Yao Liu, Phani Vaddadi, Vish Vadlamani