"AI-Trader: Can AI Beat the Market?"

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.

Fast and memory-efficient exact attention

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

slime is an LLM post-training framework for RL Scaling.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

A high-performance inference engine for LLMs, optimized for diverse AI accelerators.

🦜🔗 Build context-aware reasoning applications

2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，思想类，数学类，人物传记书籍

Large Language Model (LLM) Systems Paper List

A framework for generating realistic LLM serving workloads

Awesome LLMs on Device: A Comprehensive Survey

Kimi K2 is the large language model series developed by Moonshot AI team

A collection of prompts, system prompts and LLM instructions

关于2025年CS保研实验室/导师招生广告的汇总。欢迎想要打广告的小伙伴积极PR，资瓷一下互联网精神吼不吼啊？

Tile primitives for speedy kernels

verl: Volcano Engine Reinforcement Learning for LLMs

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Universal LLM Deployment Engine with ML Compilation

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

中国大模型

A Datacenter Scale Distributed Inference Serving Framework