Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs

Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication feat…

Puzzles for learning Triton

The missing pieces (as far as boilerplate reduction goes) of the upstream MLIR python bindings.

An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).

ChatGPT for wechat https://github.com/AutumnWhj/ChatGPT-wechat-bot

A scalable High-Level Synthesis framework on MLIR

Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits

Workload-Aware Co-Optimization

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time

Allo: A Programming Model for Composable Accelerator Design

Development repository for the Triton language and compiler

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

The Tensor Algebra Compiler (taco) computes tensor expressions on sparse and dense tensors

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming

Dataflow dialect

generating hardware accelerators for pangenomic graph queries

TAPA is a dataflow HLS framework that features fast compilation, expressive programming model and generates high-frequency FPGA accelerators.

SparseTIR: Sparse Tensor Compiler for Deep Learning

Serpens is an HBM FPGA accelerator for SpMV

GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks