isHuangXin
Follow
Highlights
- Pro
Stars
How to make undergraduates or new graduates ready for advanced computer architecture research or modern CPU design
Efficient and easy multi-instance LLM serving
Disaggregated serving system for Large Language Models (LLMs).
PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
A distributed, fast open-source graph database featuring horizontal scalability and high availability
The code for the paper "Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval" (WWW'22).
Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
A Microkernel OS Lab & Note & Homework for SJTU SE3357
My solution to the labs of the book "Modern Operating System: Principle and Implementation" by Haibo Chen
收集全国各高校招生时不会写明，却会实实在在影响大学生活质量的要求与细节
[OSDI 2024] Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory
This is the tool released in the ASE'23 paper "Generative Type Inference for Python".
Tensors and Dynamic neural networks in Python with strong GPU acceleration
lightweight, standalone C++ inference engine for Google's Gemma models.
本项目为华科（华中科技大学）本科生毕业论文的进阶优化版Word模板。它源于官方但高于官方，由于官方的Word模板难以使用且问题多多，自动化程度低，故有本项目。本项目为在页码、封面、分级标题、数学公式、图表题注、交叉引用、参考文献引用等方面做出了优化后的Word模板。
WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices,…
Zero-shot Document Ranking with Large Language Models.