AcadHomepage: A Modern and Responsive Academic Personal Homepage

RapidStream TAPA compiles task-parallel HLS program into high-frequency FPGA accelerators.

The official PyTorch implementation of Google's Gemma models

Serpens is an HBM FPGA accelerator for SpMV

Feature selection in neural networks

(ICML 2024) BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Allo: A Programming Model for Composable Accelerator Design

General technology for enabling AI capabilities w/ LLMs and MLLMs

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Serving multiple LoRA finetuned LLM as one

TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

PyTorch Tutorials from my YouTube channel

Re-implementation of the TASO compiler using equality saturation

egraphs good