Cheng Wan's starred repositories
Awesome-Efficient-LLM
A curated list for Efficient Large Language Models
benchmarking-gnns
Repository for benchmarking graph neural networks
awesome-AI-system
paper and its code for AI System
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
awesome-neural-rendering
Resources of Neural Rendering
dsa-framework
Release of stream-specialization software/hardware stack.
awesome-gnn-systems
A list of awesome GNN systems.
Citation_Parser
Automatically citation parsing from Google Scholar and Researchgate for creating Github badges
DepthShrinker
[ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin
Awesome-Federated-Learning-on-Graph-and-GNN-papers
Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.
only_train_once
OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM
Robust-Scratch-Ticket
[NeurIPS 2021] "Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks" by Yonggan Fu, Qixuan Yu, Yang Zhang, Shang Wu, Xu Ouyang, David Cox, Yingyan Lin
mirror-docker-unified
Infrastructure of SJTUG mirrors
wikipedia2vec
A tool for learning vector representations of words and entities from Wikipedia
markov-painting
Procedural art generation from Markov Chain