SGLang is a high-performance serving framework for large language models and multimodal models.
Repository Index
132,241 visible repositories in the index
1–24 of 73 · Most stars
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
- diffusion
- dit
- pytorch
- sana
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
- gan
- cyclegan
- pix2pix
- super-resolution
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe
open Structure-fom-Motion and Multi-View Stereo reconstruction library
- multi-view-stereo
- 3d-reconstruction
- point-cloud
- stereo-reconstruction-library
CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️
- ai
- huggingface
- llm
- management-system
Collection of generative models in Tensorflow
- gan
- vae
- cgan
- infogan
🏆 Self Hosted Gen AI desktop app. Free alternative to Higgsfield, OpenArt, Freepik....
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
torch-optimizer -- collection of optimizers for Pytorch
- pytorch
- optimizer
- diffgrad
- adamod
An optimizer that trains as fast as Adam and as good as SGD.
Collection of generative models in Pytorch version.
A Deep Learning Approach for Password Guessing (https://arxiv.org/abs/1709.00440)
- password-cracking
- machine-learning
- deep-learning
- gan
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
- deep-learning
- bayesian-inference
- pytorch
- reproducible-research
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
- 3d-generation
- 3d-reconstruction
- image-to-3d
- 3d-genai
《明日方舟》游戏数据
High Performance Serving Runtime For Interactive Super Intelligence System
PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
- int4
- quantization
- rounding
- transformers
[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang
- transformer
- transformer-encoder
- transformer-models
- gan
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
- reinforcement-learning
- parallel-processing
- cpp17
- pybind11
[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning
- large-language-models
- speech-dialogue-generation
- finetune
- sglang