Search Results for author:
Found 3 papers, 2 papers with code
CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
We demonstrate that CATS can be applied to various base models, including Mistral-7B and Llama2-7B, and outperforms existing sparsification techniques in downstream task performance.
GeoT: Tensor Centric Library for Graph Neural Network via Efficient Segment Reduction on GPU
Yet, efficient tensor-centric frameworks for GNNs remain scarce due to unique challenges and limitations encountered when implementing segment reduction in GNN contexts.
Canvas: End-to-End Kernel Architecture Search in Neural Networks
KAS reviews NAS from a system perspective and zooms into a more fine-grained level to generate neural kernels with both high performance and good accuracy.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
