Open Machine Learning Compiler Framework

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

Serving multiple LoRA finetuned LLM as one

Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

Latency and Memory Analysis of Transformer Models for Training and Inference

Neural Network Tools: Converter and Analyzer. For caffe, pytorch, draknet and so on.

Provide Python access to the NVML library for GPU diagnostics

Research and development for optimizing transformers

An infrastructure for integrated EDA

Reproduce Fast ConvNets @CVPR 2020