Stars
LLM KV Cache compression - K+V dual compression, 73-99% VRAM savings, zero accuracy loss
T0-GPU is a pure-Rust GPU programming framework targeting AMD RDNA3 (GFX1100) hardware. It bypasses HIP/ROCm userspace libraries entirely, communicating directly with the GPU through the Linux KFD …
Scholar All-In-One: A research infrastructure for AI agents
A PyTorch coding practice platform — covering LLM, Diffusion, PEFT, and more A friendly environment to help you deeply understand deep learning components through hands-on practice. Like LeetCode, …
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
🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...
视频号、小程序、抖音、快手、小红书、直播流、m3u8、酷狗、QQ音乐等常见网络资源下载!
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
A coding agent for open models like Kimi K3
本项目面向课堂教学，目标是让初学者用一台普通 CPU 电脑，在 45 分钟内从零跑通一个小参数的中文 GPT：看清核心流程、跑通训练、得到“可用的中文回答”，并支持简单的推理演示。
Kimi K2 Thinking Agentic Search Unofficial Implementation
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
uygnef / verl
Forked from verl-project/verlverl: Volcano Engine Reinforcement Learning for LLMs
Benchmark vllm with different parallel settings
2025 最新校招面试题合集， 面向 2026 届应届生，全网最全整理！收录 1000+道真实面试题以及面经，涵盖阿里、腾讯、字节、美团、百度、华为、小米、英伟达、微软、米哈游等百家大中小厂。每题配备视频解析 or 文字讲解，持续更新中，助力拿下 Dream Offer！
Automated tool for running Python programs in a streamlined manner
SongGeneration:High-Quality Song Generation with Multi-Preference Alignment (SOTA),you can try VRAM>12G
sagieppel / fine-tune-train_segment_anything_2_in_60_lines_of_code
Forked from facebookresearch/sam2The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)
solrex / cutlass
Forked from NVIDIA/cutlassCUDA Templates for Linear Algebra Subroutines