Development repository for the Triton language and compiler

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

FlashMLA: Efficient Multi-head Latent Attention Kernels

TiNET is network emulator environment for network function developer, routing software developer and networking educator. this is very simple tool that generate just shell script to construct virtu…

Multilingual Voice Understanding Model

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

Physics of Language Models, Part 4

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.

Official SeedVR2 Video Upscaler for ComfyUI

计算机自学指南

[NeurIPS'25] One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

Nano vLLM

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

PyTorch code and models for VJEPA2 self-supervised learning from video.

A latent text-to-image diffusion model

Official inference repo for FLUX.1 models

Open-source unified multimodal model

[NeurIPS 2025] MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

Material for gpu-mode lectures

所有小初高、大学PDF教材。

YOLO Face 🚀 in PyTorch

Official implementation for the paper "DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability"