A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.
- flux2-klein
- svdquant
- flux3
- flux3-klein
111,821 visible repositories in the index
1,489–1,512 of 2,921 · Most stars
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.
A script for building turnip driver as an adrenotool package from mesa repository, scheduled releases per 2 week via github actions.
Repositório das lives de python semanais
[ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"
ClickHouse Python Driver with native interface support
Zero Breach — local, read-only scanner that checks a computer for indicators of the AdFection / Candiru ad-delivered spyware campaign. No network, no admin, no dependencies.
DLSS 5 NR on your whole Windows desktop, in real time with Boost, FG, etc. RTX 30/40/50, 12 languages, user presets, recording with audio, one-window mode.
Mirror of FreeIPA, an integrated security information management solution
Intuitive, easy CLIs based on python type hints.
AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies
:couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:
Generating sets of formulaic alpha (predictive) stock factors via reinforcement learning.
Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
An Interactive Binary Patching Plugin for IDA Pro
Terraform textual UI
A comprehensive, step-by-step guide to learning Machine Learning from absolute basics to advanced topics
Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.
Official Inference Code of EAGLE-4
Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
⚡ Competitive Programming Library
A 3DGS framework for omni urban scene reconstruction and simulation.
Turn AI-written copy into copy a human would ship. Lint for AI tells, cleanse with a rival model, lint again.