wdl339

ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, MiniCPM, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, GraphRAG, DeepSpeed, vLLM, FastChat, Axolotl, etc.

wdl339.github.io

个人博客主页

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

mlc-llm

Universal LLM Deployment Engine with ML Compilation

CSAPP-Labs

交大软工IPADS金课ICS（计算机系统基础）全套lab代码，教材为CSAPP，基本全满分

ChatBotApp

mllm

Fast Multimodal LLM on Mobile Devices

compose-samples

Official Jetpack Compose samples.

todo-nodejs

自制网页版todo list，更适合SJTUer体质的todo list，这里是后端代码

LSMKV

SJTU ADS（高级数据结构）课程project，从零实现LSMKV键值存储系统，具有键值分离、垃圾回收等特性

ADS-lab-HNSW

SJTU ADS（高级数据结构）课程lab，实现HNSW

todo-reactjs

自制网页版todo list，更适合SJTUer体质的todo list，这里是前端代码

ADS-lab1-Radix-tree

SJTU ADS（高级数据结构）课程lab，实现radix tree

LSTM-for-anti-spam-mail

使用LSTM模型与openvino加速的AI模型，可智能识别垃圾邮件、诈骗邮件内容，SJTU学创中心 英特尔ai前沿算法实践课程大作业

QBasic

QBasic，SJTU SEP课程期末大作业，使用QT Creator开发的Basic解释器

QLink

QLink连连看，SJTU SEP暑期满分大作业，使用QT开发，星穹铁道主题