Coleman Hooper

发表

Full Stack Optimization of Transformer Inference: a Survey

Michael W. Mahoney, K. Keutzer, A. Gholami, 2023, ArXiv.

A 16-nm SoC for Noise-Robust Speech and NLP Edge AI Inference With Bayesian Sound Source Separation and Attention-Based DNNs

Alexander M. Rush, Glenn G. Ko, Gu-Yeon Wei, 2023, IEEE Journal of Solid-State Circuits.

EdgeBERT: Optimizing On-Chip Inference for Multi-Task NLP

Alexander M. Rush, Gu-Yeon Wei, D. Brooks, 2020, ArXiv.

EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference

Alexander M. Rush, David Brooks, Paul N. Whatmough, 2020, MICRO.

SqueezeLLM: Dense-and-Sparse Quantization

Michael W. Mahoney, K. Keutzer, Zhen Dong, 2023, ArXiv.

Full Stack Optimization of Transformer Inference

Michael W. Mahoney, K. Keutzer, A. Gholami, 2023 .

Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models pdf

Thierry Tambe, Coleman Hooper, Gu-Yeon Wei, 2021, ArXiv.

9.8 A 25mm2 SoC for IoT Devices with 18ms Noise-Robust Speech-to-Text Latency via Bayesian Speech Denoising and Attention-Based Sequence-to-Sequence DNN Speech Recognition in 16nm FinFET

Alexander M. Rush, Gu-Yeon Wei, David Brooks, 2021, 2021 IEEE International Solid- State Circuits Conference (ISSCC).

22.9 A 12nm 18.1TFLOPs/W Sparse Transformer Processor with Entropy-Based Early Exit, Mixed-Precision Predication and Fine-Grained Power Management

Alexander M. Rush, Kenneth E. Shepard, Gu-Yeon Wei, 2023, IEEE International Solid-State Circuits Conference.

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Lianmin Zheng, I. Stoica, Coleman Hooper, 2023, ArXiv.

SqueezeLLM: Dense-and-Sparse Quantization

Michael W. Mahoney, K. Keutzer, Zhen Dong, 2023, ArXiv.

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

A. Gholami, Y. Shao, Sehoon Kim, 2024, ArXiv.

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Lianmin Zheng, Coleman Hooper, Ying Sheng, 2023, ArXiv.