Pinned Repositories
ae-gnn-MLSys-22
Optimization of GNN's GPU Computation with kernel fusion & activation recomputation
asplos24-GMT
GMT: GPU Orchestrated Memory Tiering for the Big Data Era
awesome-gnn-systems
A list of awesome GNN systems.
awesome-graph-transformer
Papers about graph transformers.
Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
graph-based-deep-learning-literature
links to conference publications in graph-based deep learning
Literatures-on-GNN-Acceleration
A reading list for deep graph learning acceleration.
LMC-ICLR-23
Convergence Improvement of GNNAutoScale (Historical Embedding based Sampling method)
PaGraph-SoCC-20
Data Transmission Optimization by Static Feature Caching in GPU Memory
PipeGCN-ICLR-22
GNN Full-Batch Optimization by overlapping inter-partition communication with intra-partition computation
junesookang's Repositories
junesookang/asplos24-GMT
GMT: GPU Orchestrated Memory Tiering for the Big Data Era
junesookang/ae-gnn-MLSys-22
Optimization of GNN's GPU Computation with kernel fusion & activation recomputation
junesookang/awesome-gnn-systems
A list of awesome GNN systems.
junesookang/awesome-graph-transformer
Papers about graph transformers.
junesookang/Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
junesookang/GNNLab-EuroSys-23
Optimization of Data Transmission and Data Sampling of GNN by feature caching in GPU Memory, Sampling in GPU
junesookang/graph-based-deep-learning-literature
links to conference publications in graph-based deep learning
junesookang/Literatures-on-GNN-Acceleration
A reading list for deep graph learning acceleration.
junesookang/LMC-ICLR-23
Convergence Improvement of GNNAutoScale (Historical Embedding based Sampling method)
junesookang/PaGraph-SoCC-20
Data Transmission Optimization by Static Feature Caching in GPU Memory
junesookang/PipeGCN-ICLR-22
GNN Full-Batch Optimization by overlapping inter-partition communication with intra-partition computation
junesookang/SALIENT-plusplus-MLSys-23
Communication-Efficient GNN with Probabilistic Neighborhood Expansion Analysis and Caching
junesookang/torch-quiver
PyTorch Library for Low-Latency, High-Throughput Graph Learning on GPUs.