70,736 visible repositories in the index
97–120 of 209 · 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.
🎚️ Open Source Audio Matching and Mastering
Awesome Deep Learning papers for industrial Search, Recommendation and Advertisement. They focus on Embedding, Matching, Pre-Ranking, Ranking, Post Ranking, Relevance, LLM and RL. Please cite our paper "Deep Learning to Rank in Industrial Search Engines, Recommender Systems, and Online Advertising - An Overview and New Perspectives" (TOIS 2026).
TorchCFM: a Conditional Flow Matching library
Repository containing evidence of police brutality during the 2020 George Floyd protests
Fast, accurate and scalable probabilistic data linkage with support for multiple SQL backends
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
Simple, modern and fast file watching and code reload for Python, written in Rust
:watch: A wonderful CLI to track your time!
TranslatedPanWatch — AI stock monitoring for A-shares, HK & US markets, powered by TradingAgents. Portfolio insights, real-time alerts & automated reports.
AutoSwarm: Unify All Your Agents. Break Context Barriers. Watch Them Work Together for You.
A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
A framework for large scale recommendation algorithms.
A Python module for decorators, wrappers and monkey patching.
Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Master the fundamentals of machine learning, deep learning, and mathematical optimization by building key concepts and models from scratch using Python.
ChatGPT Plus/Team/Pro 订阅协议端到端重放工具集 · hCaptcha 视觉求解器 · 反欺诈机制实证研究 / End-to-end protocol replay toolkit for ChatGPT Plus/Team/Pro subscription with from-scratch hCaptcha solver and empirical anti-fraud research
Privacy and security enhanced releases of Chromium for GrapheneOS. Vanadium provides the WebView and standard user-facing browser on GrapheneOS. It depends on hardening in other GrapheneOS repositories and doesn't include patches not relevant to the build targets used on GrapheneOS.
A TensorFlow & Deep Learning online course I taught in 2016
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
BLE monitor for passive BLE sensors
哈喽！龙虾 🙋♀️ Adopt from scratch and build your first claw 🦞 来领养你的第一只龙虾！