Stars
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A high-throughput and memory-efficient inference and serving engine for LLMs
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
A modular graph-based Retrieval-Augmented Generation (RAG) system
A collection of resources on dynamic/streaming/temporal/evolving graph processing systems, databases, data structures, datasets, and related academic and industrial work
The Overleaf LaTeX template of the bupt graduate thesis.
⏰ Collaboratively track deadlines of conferences recommended by CCF (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~
Latest Advances on System-2 Reasoning
FlashSparse significantly reduces the computation redundancy for unstructured sparsity (for SpMM and SDDMM) on Tensor Cores through a Swap-and-Transpose mapping strategy. FlashSparse is accepted by…
Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.
scikit-learn: machine learning in Python
A Python scikit for building and analyzing recommender systems
library to read/write .npy and .npz files in C/C++
Code for High Performance Unstructured SpMM Computation Using Tensor Cores
The book "Performance Analysis and Tuning on Modern CPU"
Methods in Algebra (Volume 1): A Chinese textbook on Algebra
Artifact for USENIX ATC'23: TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs.
PyTorch-Based Fast and Efficient Processing for Various Machine Learning Applications with Diverse Sparsity
Python package built to ease deep learning on graph, on top of existing DL frameworks.
A pytorch package for non-negative matrix factorization.