Research Projects

CPU-GPU Orchestration for Fast Inference of MoE Models

Serving multiple LoRA finetuned LLM as one

Low-bit Quantization for Efficient and Accurate LLM Serving

Kernel Library for LLM Serving

Compiler for Sparsity in Deep Learning

Checkpointing deep learning models as a dynamic analysis

Low-level Intermediate Representation (IR) for Programming Modern FPGAs

Hardware-software partition exploration with e-graphs.

Parameter Server for Efficient Distributed Deep Neural Network Training for Clusters, Datacenters, and the Public Clouds

High level IR for optimizing machine learning models.

Hardware/Software Deep Learning Acceleration Stack

Fast Video Classification via Adaptive Cascading of Deep Models

TVM: An Automated End-to-End Optimizing Compiler for Deep Learning

A Scalable Tree Boosting System