Vicki Boykis
@vboykis
I gave a talk last night at DataPhilly on inference in production with ONNX and ONNXRT and the differences between generative and embedding architectures, and where both have a place in information retrieval systems, slides are here.
https://vickiboykis.com/2026/10/29/slides-on-retrieval-and-ranking-with-onnx-inference/