ceku7
Follow
Stars
PCBox / PCBox
Forked from 86Box/86BoxEmulator of PC-based machines based on 86Box.
This is a collection of requiered ROMs files for PCem emulator. RIP PCem 2021
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
Quantized Attention achieves speedup of 2-3x and 3-5x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.
A quick guide (especially) for trending instruction finetuning datasets
PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"
Official PyTorch codes for "Enhancing Diffusion Models with Text-Encoder Reinforcement Learning", ECCV2024
Production-Grade Container Scheduling and Management
PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)
A latent text-to-image diffusion model
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Efficient vision foundation models for high-resolution generation and perception.
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
Official inference repo for FLUX.1 models
Implementation of the proposed MaskBit from Bytedance AI
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory…
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
Open-Sora: Democratizing Efficient Video Production for All
Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"