An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

LeetCode solutions

SGLang is a high-performance serving framework for large language models and multimodal models.

📕 小红书创作者MCP工具包 - 支持与AI客户端集成的内容创作和发布工具

Democratizing Reinforcement Learning for LLMs

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient

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

Writing reviews of academic papers

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

Truly flash T5 realization!

Curated list of datasets and tools for post-training.

Replication code for semantic ID generation in “Transformer Memory as a Differentiable Search Index”.

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

Integrate the DeepSeek API into popular software

Language Models as Semantic Indexers (ICML 2024)

Residual Quantization with Implicit Neural Codebooks

This repository includes all the interview preparation questions for Amazon SDE role

🎮 A curated list of awesome game datasets, and tools to artificial intelligence in games

Sample codes for my CUDA programming book

CUDA Library Samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Let your Claude able to think

This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

A curated list of previous asked Interview Question at Big Companies and Startups 🤲 🏆