8000 xiaoyaozhuzi / Starred · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View xiaoyaozhuzi's full-sized avatar

Block or report xiaoyaozhuzi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

Python 151 12 Updated May 20, 2025

EEdit⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing

Python 27 1 Updated Mar 19, 2025

Accelerating Diffusion Transformers with Token-wise Feature Caching

Python 147 4 Updated Mar 14, 2025

Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache).

Python 53 2 Updated May 27, 2025

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Python 18,580 1,878 Updated May 27, 2025

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

Python 505 46 Updated May 27, 2025
Python 329 24 Updated Mar 20, 2025

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

Python 1,104 165 Updated May 27, 2025

Lets make video diffusion practical!

Python 13,757 1,188 Updated May 4, 2025

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Python 29,529 3,495 Updated May 27, 2025

LTX-Video Support for ComfyUI

Python 1,969 168 Updated May 14, 2025

verl: Volcano Engine Reinforcement Learning for LLMs

Python 8,578 1,064 Updated May 28, 2025

VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework

Python 331 14 Updated May 12, 2025

Efficient Triton Kernels for LLM Training

Python 5,100 334 Updated May 27, 2025

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

Python 363 20 Updated May 27, 2025

A pipeline parallel training script for diffusion models.

Python 1,069 127 Updated May 27, 2025

A fast communication-overlapping library for tensor/expert parallelism on GPUs.

C++ 955 60 Updated Apr 15, 2025

Wan: Open and Advanced Large-Scale Video Generative Models

Python 11,735 1,348 Updated May 27, 2025

[CVPR2025 Highlight] SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

74 Updated Mar 7, 2025

Unofficial Windows wheel package for the Nunchaku (SVDQuant) library.

15 2 Updated Mar 9, 2025

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Python 11,467 1,105 Updated May 14, 2025

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.

Cuda 1,589 112 Updated May 22, 2025

CUDA Library Samples

Cuda 1,952 390 Updated May 19, 2025

Distributed Triton for Parallel Systems

Python 765 49 Updated May 26, 2025

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Python 1,014 56 Updated May 22, 2025
Python 2,127 205 Updated Apr 28, 2025

[ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

Python 222 10 Updated Dec 27, 2024

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Python 825 33 Updated May 25, 2025

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

Python 288 27 Updated May 13, 2025
Next
0