Enhancements of "TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training" by Krause et al.

The official repository for tariff

Threading and Multiprocessing made easy.

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

(jax, tpu) nf4 matmuls for flux + t5 + onnx vae. vision SAE training and maxacts

Official inference repo for FLUX.1 models

NVIDIA Linux open GPU with P2P support

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Tensors, for human consumption

a state-of-the-art-level open visual language model | 多模态预训练模型

A fast inference library for running LLMs locally on modern consumer-class GPUs

Web UI for ExLlamaV2

Cross-Platform, GPU Accelerated Whisper 🏎️

EVA Series: Visual Representation Fantasies from BAAI

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

NVJpeg torch extension

Nightly release of ControlNet 1.1

Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

A multi-voice TTS system trained with an emphasis on quality

Remove text from AI-generated images

Chopsticks is an orchestration library: it lets you execute Python code on remote hosts over SSH.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

stable diffusion finetuned on weeb stuff

An implementation of a server for the Stability AI Stable Diffusion API

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Robust Speech Recognition via Large-Scale Weak Supervision

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Tensors and Dynamic neural networks in Python with strong GPU acceleration