5 papers · 1 filter
Fast KV Compaction via Attention Matching
Adam Zweiger, Xinghong Fu, Han Guo +1
Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction…
Self-Adapting Language Models
Adam Zweiger, Jyothish Pari, Han Guo +3
Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs…
Log-Linear Attention
Han Guo, Songlin Yang, Tarushii Goel +3
The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain sig…
On the Duality between Gradient Transformations and Adapters
Lucas Torroba-Hennigen, Hunter Lang, Han Guo +1
We study memory-efficient optimization of neural networks (in particular language models) with linear gradient transformations, where the gradients are linearly mapped to a lower d…
Fast Matrix Multiplications for Lookup Table-Quantized LLMs
Han Guo, William Brandon, Radostin Cholakov +3
The deployment of large language models (LLMs) is often constrained by memory bandwidth, where the primary bottleneck is the cost of transferring model parameters from the GPU's gl…