Picture for Jonathan Ragan-Kelley

Jonathan Ragan-Kelley

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

Add code
Jul 15, 2024
Viaarxiv icon

WatChat: Explaining perplexing programs by debugging mental models

Add code
Mar 08, 2024
Figure 1 for WatChat: Explaining perplexing programs by debugging mental models
Figure 2 for WatChat: Explaining perplexing programs by debugging mental models
Figure 3 for WatChat: Explaining perplexing programs by debugging mental models
Figure 4 for WatChat: Explaining perplexing programs by debugging mental models
Viaarxiv icon

Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Add code
Feb 07, 2024
Viaarxiv icon

How to guess a gradient

Add code
Dec 07, 2023
Figure 1 for How to guess a gradient
Figure 2 for How to guess a gradient
Figure 3 for How to guess a gradient
Figure 4 for How to guess a gradient
Viaarxiv icon

Striped Attention: Faster Ring Attention for Causal Transformers

Add code
Nov 15, 2023
Viaarxiv icon

The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning

Add code
Oct 07, 2023
Figure 1 for The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Figure 2 for The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Figure 3 for The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Figure 4 for The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Viaarxiv icon

Differentiating Metropolis-Hastings to Optimize Intractable Densities

Add code
Jun 30, 2023
Figure 1 for Differentiating Metropolis-Hastings to Optimize Intractable Densities
Figure 2 for Differentiating Metropolis-Hastings to Optimize Intractable Densities
Figure 3 for Differentiating Metropolis-Hastings to Optimize Intractable Densities
Figure 4 for Differentiating Metropolis-Hastings to Optimize Intractable Densities
Viaarxiv icon

Acting as Inverse Inverse Planning

Add code
May 26, 2023
Figure 1 for Acting as Inverse Inverse Planning
Figure 2 for Acting as Inverse Inverse Planning
Figure 3 for Acting as Inverse Inverse Planning
Figure 4 for Acting as Inverse Inverse Planning
Viaarxiv icon

Inferring the Future by Imagining the Past

Add code
May 26, 2023
Figure 1 for Inferring the Future by Imagining the Past
Figure 2 for Inferring the Future by Imagining the Past
Figure 3 for Inferring the Future by Imagining the Past
Figure 4 for Inferring the Future by Imagining the Past
Viaarxiv icon

Designing Perceptual Puzzles by Differentiating Probabilistic Programs

Add code
Apr 26, 2022
Figure 1 for Designing Perceptual Puzzles by Differentiating Probabilistic Programs
Figure 2 for Designing Perceptual Puzzles by Differentiating Probabilistic Programs
Figure 3 for Designing Perceptual Puzzles by Differentiating Probabilistic Programs
Viaarxiv icon