Allen Philip

Allen Philip is a senior machine learning engineer on Adobe's Firefly team, where he leads the inference optimization squad in India. His work centers on wringing performance out of video and audio inference pipelines, with a sharp focus on quantization, attention optimization, and TensorRT.
Avatar photo

Posts by Allen Philip

Development & Optimization Apr 21, 2025

Optimizing Transformer-Based Diffusion Models for Video Generation with NVIDIA TensorRT

State-of-the-art image diffusion models take tens of seconds to process a single image. This makes video diffusion even more challenging, requiring significant... 8 MIN READ