Highlights
- Pro
Stars
MiniCPM5: SOTA on-device LLMs, small yet powerful.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Speedrun for pretraining without backpropagation
GPT Image 2/2.5/2.6 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Defend sound research against LLM reviewer bias through meaning-preserving rewrites.
FlashKDA: high-performance Kimi Delta Attention kernels
Itssshikhar / Flash-Flash-KDA
Forked from MoonshotAI/FlashKDAFlash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
DeepSeek Harness: Everything is a Plugin.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
A curated list of papers and selected technical blogs on Loop Models.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
分享AI Infra知识&代码练习:PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…
Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (Technical Report)
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
A benchmark for evaluating AI agents on realistic business workflows
Best practices, reference architectures, and examples for distributed AI training and inference on AWS.
Efficient Triton Kernels for LLM Training
The NoteBook and Assignments implemention via Learning CS336 Spring 2026😛
Real-time Claude Code usage monitor with predictions and warnings