Cite
Notes
Only stored in your browser.
Attribution
CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
arXiv 2025
Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels
arXiv 2024
Enhancing Transformer RNNs with Multiple Temporal Perspectives
from 3 papers
Mihai Surdeanu
Vikas Yadav
Darius Peteleaza
Minglai Yang
Paul-Ioan Clotan
Rishabh Maheshwary
Sathwik Tejaswi Madhusudhan