SGLang is a high-performance serving framework for large language models and multimodal models.

The official implementation of paper "STOW: Discrete-Frame Segmentation and Tracking of Unseen Objects for Warehouse Picking Robots" at CoRL 2023

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

Minimal reproduction of DeepSeek R1-Zero

Fully open reproduction of DeepSeek-R1

PyTorch code and models for the DINOv2 self-supervised learning method.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Main repository for Vispy

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Deep Iterative Matching for 6D Pose Estimation

Deformable Convolutional Networks + MST + Soft-NMS

Python+Numpy+OpenGL: fast, scalable and beautiful scientific visualization

Reproduce ResNet-v2(Identity Mappings in Deep Residual Networks) with MXNet

Semantic Mapping with Data Associated Recurrent Neural Networks

Deep Feature Flow for Video Recognition

Fully Convolutional Instance-aware Semantic Segmentation

Deformable Convolutional Networks

Assignments for CS294-112.

R-FCN with joint training and python support

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Caffe branch for MNC

Caffe branch for R-FCN

Instance-aware Semantic Segmentation via Multi-task Network Cascades