Programmable CUDA/C++ GPU Graph Analytics

Benchmarking Deep Learning operations on different hardware

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

collection of benchmarks to measure basic GPU capabilities

The official repository of ALE-Bench

Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Large Language Models.

A microbenchmark support library

CUDA Kernel Benchmarking Library

Learn CUDA with PyTorch

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.

Open-source unified multimodal model

Apptainer: Application containers for Linux

A PyTorch native platform for training generative AI models

A hybrid GPU cluster simulator for ML system performance estimation

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

A Git-compatible VCS that is both simple and powerful

cloc counts blank lines, comment lines, and physical lines of source code in many programming languages.

AgentScope: Agent-Oriented Programming for Building LLM Applications

Leave One Feature Out Importance

Capabench：A Game-Theoretic Evaluation Benchmark for Modular Attribution in LLM Agents

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

Polyhedral Parallel Code Generation (source repository: http://repo.or.cz/ppcg.git)

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

A machine learning compiler for GPUs, CPUs, and ML accelerators

KMS 激活服务，slmgr 命令激活 Windows 系统、Office