HEJIAN SANG

swe-marathon. SWE-Marathon: an ultra long-horizon SWE benchmark

harbor. Framework for evaluating and improving agents

tokenspeed. TokenSpeed is a speed-of-light LLM inference engine.

CL-bench. CL-bench: A Benchmark for Context Learning

miles. Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

RL. Scalable toolkit for efficient model reinforcement

KORGym. Python

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

DAPO. An Open-source RL System from ByteDance Seed and Tsinghua AIR

yt-dlp. A feature-rich command-line audio/video downloader

Awesome-ML-SYS-Tutorial. My learning notes for ML SYS.

firecrawl. The API to search, scrape, and interact with the web at scale. 🔥

lectures. Material for gpu-mode lectures

TensorRT-LLM. TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

Aria. Codebase for Aria - an Open Multimodal Native MoE

unsloth. Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

eat_pytorch_in_20_days. Pytorch🍊🍉 is delicious, just eat it! 😋😋

open_lm. A repository for research on medium sized language models.

aimoneyhunter. ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English version for more insights.

llm-answer-engine. Perplexity Inspired Answer Engine

OpenHands. 🙌 OpenHands: AI-Driven Development

awesome-ai-agents. A list of AI autonomous agents

awesome-llm-agents. A curated list of awesome LLM agents frameworks.

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

ml-mgie. Python

Whisperboard. The open-source iOS app that's making quality voice transcription more accessible on mobile devices.

contrastors. Train Models Contrastively in Pytorch

MiniCPM. MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.

OLMo. Modeling, training, eval, and inference code for OLMo

TinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

AppAgent. AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

vision_transformer. Jupyter Notebook

Transformer-in-Vision. Recent Transformer-based CV and related works.

awesome-mlops. A curated list of references for MLOps

polkadot. Polkadot Node Implementation

JavaFamily. 【Java面试+Java学习指南】 一份涵盖大部分Java程序员所需要掌握的核心知识。

JavaGuide. Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

machine-learning-interview. Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

image-to-latex. Convert images of LaTex math equations into LaTex code.

Ad-papers. Papers on Computational Advertising

wzhe06.github.io. Wang Zhe's blog

RecLearn. Recommender Learning with Tensorflow2.x

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

leetcode-python. Leetcode Python Solution and Explanation. Also a Guide to Prepare for Software Engineer Interview.

python-coding-interview. A middle-to-high level open source algorithm book designed with coding interview at heart!

ML-NLP. 此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

tech-interview-handbook. Curated coding interview preparation materials for busy software engineers

predictionio. PredictionIO, a machine learning server for developers and ML engineers.

awesome-tensorflow. TensorFlow - A curated list of dedicated resources http://tensorflow.org

fastText. Library for fast text representation and classification.

face_recognition. The world's simplest facial recognition api for Python and the command line

stanford-tensorflow-tutorials. This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.

tensorflow. An Open Source Machine Learning Framework for Everyone

bert. TensorFlow code and pre-trained models for BERT

AdaBound. An optimizer that trains as fast as Adam and as good as SGD.

fastai. The fastai deep learning library