Stars
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
A framework for efficient model inference with omni-modality models
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
TokenSpeed is a speed-of-light LLM inference engine.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
练习下用pytorch来复现下经典的推荐系统模型, 如MF, FM, DeepConn, MMOE, PLE, DeepFM, NFM, DCN, AFM, AutoInt, ONN, FiBiNET, DCN-v2, AFN, DCAP等
whutbd / cuda-learn-note
Forked from xlite-dev/LeetCUDA🎉CUDA 笔记 / 高频面试题汇总 / C++笔记，个人笔记，更新随缘: sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Lumina Robotics Talent Call | Lumina社区具身智能招贤榜 | A list for Embodied AI / Robotics Jobs (PhD, RA, intern, etc
Twinkle✨: Training workbench to make your model glow.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
High Performance LLM Inference Operator Library
Production-grade client-side tracing, profiling, and analysis for complex software systems.
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Composable and Embeddable Communication Runtime for Distributed AI Services
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Whisper command line client compatible with original OpenAI client based on CTranslate2.
A PyTorch native platform for training generative AI models
A Next-Generation Training Engine Built for Ultra-Large MoE Models