A tool for working with stacked MRs on gitlab.

Cute layout visualization

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

Triton-based Symmetric Memory operators and examples

A fast communication-overlapping library for tensor/expert parallelism on GPUs.

Github mirror of trition-lang/triton repo.

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

A Bionic Reading Extension for Zotero with Verbs and Nouns Highlight

Bionic reading experience with Zotero.

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

CUDA Core Compute Libraries

DeepEP: an efficient expert-parallel communication library

A massively parallel, high-level programming language

CXLMemSim: A pure software simulated CXL.mem for performance characterization

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

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

NVIDIA Linux open GPU kernel module source

Fastest kernels written from scratch

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

A high-performance, Pythonic language for bioinformatics

Dynamic Memory Management for Serving LLMs without PagedAttention

File system and storage benchmark that uses a custom language to generate a large variety of workloads.

Multi-DBMS SQL Benchmarking Framework via JDBC

Ancillary open source software to support confidential computing on NVIDIA GPUs

Helpful tools and examples for working with flex-attention

Submit stacked diffs to GitHub on the command line

Python library for embedding inference of relational tables.

Hyrise is a research in-memory database.