Lists (1)
Stars
🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into LLMs via sparse retrieval PEFT without increasing inference FLOPs / DeepSeek Engram 架构的非…
Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.
This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed.
Achieve state of the art inference performance with modern accelerators on Kubernetes
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
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
GRID: Generative Recommendation with Semantic IDs
Demo of a customer service use case implemented with the OpenAI Agents SDK
[ICLR 2025] The implementation of paper "Preference Diffusion for Recommendation"
Diffusion-Based ECG Noise Quantification via Anomaly Detection
[ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"
Repository of KDD 25 Paper "Paper-Level Computerized Adaptive Testing for High-Stakes Examination via Multi-Objective Optimization"
MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io
🚀 The fast, Pythonic way to build MCP servers and clients.
[SIGIR 2025] implementation of AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings
Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
The LLMOPT project offers a comprehensive set of resources, including the model, dataset, training framework, and inference code, enabling users to fully utilize LLMOPT.
Long CoT Fine-Tuning and Reinforcement Learning for LLMs in the Context of the 24-Point Game: A Toy Project
Minimal reproduction of DeepSeek R1-Zero
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step