Alert button
Picture for David Brooks

David Brooks

Alert button

Generative AI Beyond LLMs: System Implications of Multi-Modal Generation

Dec 22, 2023
Alicia Golden, Samuel Hsia, Fei Sun, Bilge Acun, Basil Hosmer, Yejin Lee, Zachary DeVito, Jeff Johnson, Gu-Yeon Wei, David Brooks, Carole-Jean Wu

Viaarxiv icon

Hardware Resilience Properties of Text-Guided Image Classifiers

Dec 05, 2023
Syed Talal Wasim, Kabila Haile Soboka, Abdulrahman Mahmoud, Salman Khan, David Brooks, Gu-Yeon Wei

Figure 1 for Hardware Resilience Properties of Text-Guided Image Classifiers
Figure 2 for Hardware Resilience Properties of Text-Guided Image Classifiers
Figure 3 for Hardware Resilience Properties of Text-Guided Image Classifiers
Figure 4 for Hardware Resilience Properties of Text-Guided Image Classifiers
Viaarxiv icon

MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems

Oct 18, 2023
Samuel Hsia, Alicia Golden, Bilge Acun, Newsha Ardalani, Zachary DeVito, Gu-Yeon Wei, David Brooks, Carole-Jean Wu

Viaarxiv icon

Guess & Sketch: Language Model Guided Transpilation

Sep 25, 2023
Celine Lee, Abdulrahman Mahmoud, Michal Kurek, Simone Campanoni, David Brooks, Stephen Chong, Gu-Yeon Wei, Alexander M. Rush

Figure 1 for Guess & Sketch: Language Model Guided Transpilation
Figure 2 for Guess & Sketch: Language Model Guided Transpilation
Figure 3 for Guess & Sketch: Language Model Guided Transpilation
Figure 4 for Guess & Sketch: Language Model Guided Transpilation
Viaarxiv icon

Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies

Jul 04, 2023
Mehdi Rezaie, Ashley J. Ross, Hee-Jong Seo, Hui Kong, Anna Porredon, Lado Samushia, Edmond Chaussidon, Alex Krolewski, Arnaud de Mattia, Florian Beutler, Jessica Nicole Aguilar, Steven Ahlen, Shadab Alam, Santiago Avila, Benedict Bahr-Kalus, Jose Bermejo-Climent, David Brooks, Todd Claybaugh, Shaun Cole, Kyle Dawson, Axel de la Macorra, Peter Doel, Andreu Font-Ribera, Jaime E. Forero-Romero, Satya Gontcho A Gontcho, Julien Guy, Klaus Honscheid, Theodore Kisner, Martin Landriau, Michael Levi, Marc Manera, Aaron Meisner, Ramon Miquel, Eva-Maria Mueller, Adam Myers, Jeffrey A. Newman, Jundan Nie, Nathalie Palanque-Delabrouille, Will Percival, Claire Poppett, Graziano Rossi, Eusebio Sanchez, Michael Schubnell, Gregory Tarlé, Benjamin Alan Weaver, Christophe Yèche, Zhimin Zhou, Hu Zou

Figure 1 for Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies
Figure 2 for Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies
Figure 3 for Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies
Figure 4 for Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies
Viaarxiv icon

INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation

Jun 13, 2023
Yuji Chai, John Gkountouras, Glenn G. Ko, David Brooks, Gu-Yeon Wei

Figure 1 for INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
Figure 2 for INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
Figure 3 for INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
Figure 4 for INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
Viaarxiv icon

S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput

Jun 09, 2023
Yunho Jin, Chun-Feng Wu, David Brooks, Gu-Yeon Wei

Figure 1 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Figure 2 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Figure 3 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Figure 4 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Viaarxiv icon

CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning

May 04, 2023
Sai Qian Zhang, Thierry Tambe, Nestor Cuevas, Gu-Yeon Wei, David Brooks

Figure 1 for CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning
Figure 2 for CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning
Figure 3 for CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning
Figure 4 for CAMEL: Co-Designing AI Models and Embedded DRAMs for Efficient On-Device Learning
Viaarxiv icon