Cite
Notes
Only stored in your browser.
Attribution
Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
arXiv 2025
Spatial Mixture-of-Experts
arXiv 2022
Data Movement Is All You Need: A Case Study on Optimizing Transformers
arXiv 2020
Neural Parameter Allocation Search
neural-parameter-allocation-search
from 4 papers
Torsten Hoefler
Andrei Ivanov
Brad Settlemyer
Bryan A. Plummer
Julius Frost
Kate Saenko
Narasimha Reddy
Shigang Li
Susav Shrestha
Tal Ben-Nun