Name: Allen Zhu
Type: User
Company: Carnegie Mellon University
Bio: MS @ Carnegie Mellon 25' | MLE Intern @ Ericsson | Ex-SDE Intern @ SenseTime & iFLYTEK | Vanderbilt Alum
Location: Pittsburgh, PA, United States
Allen Zhu's Projects
My Profile
Inference optimization of the BERT model using TensorRT, NVIDIA's high-performance deep learning inference platform. TensorRT is designed to maximize the efficiency of deep learning models during inference, particularly on NVIDIA GPUs. By integrating TensorRT with BERT, we aim to significantly enhance the speed, efficiency, and performance of BERT
Data-efficient and weakly supervised computational pathology on whole slide images - Nature Biomedical Engineering
This is the combined collection of the course notes that I took for some of the computer science classes at CMU.
ๅดๆฉ่พพ่ๅธ็ๆบๅจๅญฆไน ่ฏพ็จไธชไบบ็ฌ่ฎฐ
่ฎก็ฎๆบ่ชๅญฆๆๅ
Proof-of-Work Blockchain Consensus System: A high-performance, modular implementation of a decentralized blockchain network This project is a robust and scalable implementation of a Proof-of-Work (PoW) blockchain consensus system
Distributed Multiclient Game Server: A Scalable and Concurrent Multiplayer Gaming Platform: Implementation of a robust, distributed, and scalable multiclient game server designed to support concurrent multiplayer gaming with high reliability and efficiency, leveraging Go's powerful concurrency features
GPT-powered chat for documentation, chat with your documents
Enhanced APACHE survival prediction score through machine learning
A filesystem-like contents manager for multiple backends in Jupyter
LLM Inference Engine: High-performance CUDA-accelerated framework for large language model inference A cutting-edge, open-source implementation of a large language model (LLM) inference engine, optimized for consumer-grade hardware. This project showcases advanced techniques in GPU acceleration, memory management, and algorithmic optimizations
Curated list of project-based tutorials
A pipeline to segment tissue from the background in histological images
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
MONAI Tutorials
Inference optimization of the ViT model using TensorRT, NVIDIA's high-performance deep learning inference platform. TensorRT is designed to maximize the efficiency of deep learning models during inference, particularly on NVIDIA GPUs. By integrating TensorRT with ViT, we aim to significantly enhance the speed, efficiency, and performance of ViT