Philip Kiely

Bio

Philip Kiely is the Head of Developer Relations at Baseten, where he focuses on inference infrastructure for AI applications. He is the author of "Inference Engineering," an in-depth guide covering GPU architectures, CUDA, vLLM, TensorRT-LLM, and large-scale distributed model serving. He has spoken at NVIDIA GTC, PyTorch Conference, AI Engineer World's Fair, and AWS re:Invent.