分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

ClawFeed — AI-powered news digest with structured summaries from Twitter/RSS feeds and web dashboard

Autonomous Polymarket trading agent powered by Claude Code. Expiry convergence strategy, 94.7% win rate over 2 weeks live testing.

Kimi Code CLI is your next CLI agent.

My learning notes for ML SYS.

Post-training with Tinker

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

一款便捷的抢占显卡脚本

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Scaling Deep Research via Reinforcement Learning in Real-world Environments.

🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]

adds Sequence Parallelism into LLaMA-Factory

大模型算法岗面试题(含答案):常见问题和概念解析 "大模型面试题"、"算法岗面试"、"面试常见问题"、"大模型算法面试"、"大模型应用基础"

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

A block pruning framework for LLMs.

Fully open reproduction of DeepSeek-R1

verl: Volcano Engine Reinforcement Learning for LLMs

Minimal reproduction of DeepSeek R1-Zero

System for AI Education Resource.

LiveBench: A Challenging, Contamination-Free LLM Benchmark

AllenAI's post-training codebase

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

Arena-Hard-Auto: An automatic LLM benchmark.

A simple unified framework for evaluating LLMs

The official evaluation suite and dynamic data release for MixEval.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)