Skip to content
View lswhim's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@ECNU-ILOG

Block or report lswhim

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

DFlash: Block Diffusion for Flash Speculative Decoding

Python 6,254 446 Updated Aug 18, 2026

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Python 7,326 703 Updated Jul 9, 2026

UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction

Python 159 25 Updated Aug 4, 2026

🚀 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…

Python 53 9 Updated Nov 8, 2026

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Python 1,343 89 Updated May 21, 2026

[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.

Python 1,006 108 Updated Nov 16, 2025

This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed.

Python 75 6 Updated Apr 24, 2026

State of the art inference performance with modern accelerators on Kubernetes

Python 5,330 951 Updated Nov 22, 2026

Public repository for Agent Skills

Python 198,677 23,249 Updated Nov 16, 2026
Python 6 Updated Jul 5, 2026

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

Jupyter Notebook 4,411 435 Updated Sep 20, 2026

🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.

Python 68,317 8,934 Updated Nov 21, 2026

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

Python 983 146 Updated May 18, 2026

Nano vLLM

Python 16,530 2,881 Updated Apr 26, 2026

GRID: Generative Recommendation with Semantic IDs

Python 772 135 Updated Oct 15, 2025

Minimal reproduction of OneRec

Python 1,986 296 Updated Nov 6, 2026

The unofficial implementation of Kuaishou's OneRec

Python 8 Updated Jan 25, 2026

Demo of a customer service use case implemented with the OpenAI Agents SDK

Python 6,621 1,034 Updated Dec 18, 2025

[ICLR 2025] The implementation of paper "Preference Diffusion for Recommendation"

Python 29 Updated Apr 21, 2025

Diffusion-Based ECG Noise Quantification via Anomaly Detection

Jupyter Notebook 22 Updated Mar 31, 2026

[ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"

Python 70 9 Updated Nov 20, 2025

Repository of KDD 25 Paper "Paper-Level Computerized Adaptive Testing for High-Stakes Examination via Multi-Objective Optimization"

Python 2 Updated May 25, 2026

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

Python 520 58 Updated Jul 2, 2025
Python 552 65 Updated Jan 2, 2025

A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io

Python 1,500 240 Updated Sep 14, 2026

🚀 The fast, Pythonic way to build MCP servers and clients.

Python 28,709 2,640 Updated Nov 22, 2026

[SIGIR 2025] implementation of AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings

Python 41 3 Updated Apr 15, 2025

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

C++ 2,119 349 Updated Apr 22, 2025

The LLMOPT project offers a comprehensive set of resources, including the model, dataset, training framework, and inference code, enabling users to fully utilize LLMOPT.

Python 161 16 Updated Nov 19, 2025

Long CoT Fine-Tuning and Reinforcement Learning for LLMs in the Context of the 24-Point Game: A Toy Project

Jupyter Notebook 27 Updated Feb 22, 2025
Next