Optimizing the Networks in a Parallel Fashion

Sri: To get 100 tops of compute utilization, we need to optimize across all the layers of software. We built a compiler just for neural networks that shares the structure to traditional compilers. And we have a neural network linker where we perform this link time optimization. Aigen is going to talk about how do we achieve this with the auto labeling pipeline. Thank you, Sri.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.