Applied AI experiments and examples for PyTorch

Understand Human Behavior to Align True Needs

Ongoing research training gaussian splatting at scale by distributed system

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

[CVPR 2024 Highlight] Visual Point Cloud Forecasting

[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacch…

Reference implementation of CVPR 2024 (Oral) paper "NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation"

Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

Continual Forgetting for Pre-trained Vision Models (CVPR 2024)

Training material for Nsight developer tools

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

Omnitrace: Application Profiling, Tracing, and Analysis

A GPU performance profiling tool for PyTorch models

A flexible, high-performance framework for large-scale retrieval problems based on TensorFlow.

AMD's graph optimization engine.

To make it easy to benchmark AI accelerators

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/