Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

An experimental CPU backend for Triton

Development repository for the Triton language and compiler

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

oneAPI Deep Neural Network Library (oneDNN)

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Parallel programming tutorials

Distributed Compiler based on Triton for Parallel Systems

大麦网抢票脚本

MiniOB is a compact database that assists developers in understanding the fundamental workings of a database.

Homework of Turing Students