81,337 visible repositories in the index
1,777–1,800 of 4,138 · Most stars
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
OpenTelemetry Python API and SDK
Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes
SkyReels V1: The first and most advanced open-source human-centric video foundation model
Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
Infrastructure for evolutionary AI systems. GPU-accelerated, PyTorch-based optimization with an ecosystem of algorithm libraries, benchmarks, and tools.
An implementation of the Language Server Protocol for Python
EVA Series: Visual Representation Fantasies from BAAI
ASC is a super FAST and lightweight Android decompiler designed for Agents/Mobile Researchers.
Python with braces. Because python is awesome, but whitespace is awful.
Lightweight Python library for adding real-time multi-object tracking to any detector.
Utilize misconfigured DNS and old database records to find hidden IP's behind the CloudFlare network
Deep neural network to extract intelligent information from invoice documents.
[IEEE TMI Best Paper Award] Official Implementation for UNet++
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
TranslatedTranslators is a library that aims to bring free, multiple, enjoyable translations to individuals and students in Python.
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
SNIPER / AutoFocus is an efficient multi-scale object detection training / inference algorithm
A game where you are a computer's OS and you have to manage processes, memory and I/O events.
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners
Easy benchmarking of all publicly accessible implementations of convnets
Monte Carlo tree search in JAX