Skip to content
View ichejun's full-sized avatar

Block or report ichejun

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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

Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻

Python 295 17 Updated Dec 15, 2025

Nano vLLM

Python 9,880 1,242 Updated Nov 3, 2025
Python 7,536 444 Updated Dec 14, 2025

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Python 1,070 44 Updated Oct 13, 2025

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

Python 1,351 66 Updated Oct 16, 2025

Light Video Generation Inference Framework

Python 1,256 79 Updated Dec 19, 2025

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Python 3,800 290 Updated Dec 19, 2025

Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

Python 1,055 41 Updated Dec 3, 2025

Dimple, the first Discrete Diffusion Multimodal Large Language Model

Python 113 6 Updated Jul 9, 2025

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Python 1,763 105 Updated Nov 4, 2025

dInfer: An Efficient Inference Framework for Diffusion Language Models

Python 365 34 Updated Dec 21, 2025

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Cuda 5,987 777 Updated Dec 21, 2025

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

Python 2,437 204 Updated Oct 20, 2025

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

Python 65,877 12,102 Updated Dec 21, 2025

Enjoy the magic of Diffusion models!

Python 11,181 1,054 Updated Dec 20, 2025

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Python 6,444 361 Updated Dec 19, 2025

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

Python 3,479 206 Updated Dec 21, 2025

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

Python 1,482 216 Updated Dec 15, 2025

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Python 16,336 3,242 Updated Dec 20, 2025
Python 2,483 239 Updated Jul 16, 2025

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Python 821 25 Updated Nov 25, 2025

存储一些用draw.io画的模型结构图

7 2 Updated May 27, 2020

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Python 2,071 88 Updated Dec 15, 2025

[AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Python 354 11 Updated Mar 26, 2025

Official implementation of BLIP3o-Series

Python 1,610 72 Updated Nov 29, 2025

Open-source unified multimodal model

Python 5,491 480 Updated Oct 27, 2025

所有小初高、大学PDF教材。

Roff 63,101 13,989 Updated Oct 18, 2025

Minimal Differentiable Image Reward Functions

Python 106 2 Updated Aug 19, 2025

General technology for enabling AI capabilities w/ LLMs and MLLMs

Python 4,229 357 Updated Dec 11, 2025

Cog inference for flux models

Python 367 62 Updated Jul 31, 2025
Next