Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification (NeurIPS 2021)

The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System

LLM Serving Performance Evaluation Harness

A large-scale simulation framework for LLM inference

The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System

Efficient Triton Kernels for LLM Training

A high-throughput and memory-efficient inference and serving engine for LLMs

An offline deep reinforcement learning library

Subgroup Generalization and Fairness of Graph Neural Networks

[ICLR 2021] Combining Label Propagation and Simple Models Out-performs Graph Neural Networks (https://arxiv.org/abs/2010.13993)