Activation Sequence Caching: High-Throughput and Memory-Efficient Generative Inference with a Single GPU
Year: 2024
Type: conference-paper
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
Funder: Universitas Brawijaya
Award: G7113188890
OpenAlex ID: W4403337152
