all AI news
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
May 8, 2024, 4:42 a.m. | Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
cs.LG updates on arXiv.org arxiv.org
Abstract: Efficient use of GPU memory is essential for high throughput LLM inference. Prior systems reserved memory for the KV-cache ahead-of-time, resulting in wasted capacity due to internal fragmentation. Inspired by OS-based virtual memory systems, vLLM proposed PagedAttention to enable dynamic memory allocation for KV-cache. This approach eliminates fragmentation, enabling high-throughput LLM serving with larger batch sizes. However, to be able to allocate physical memory dynamically, PagedAttention changes the layout of KV-cache from contiguous virtual memory …
abstract arxiv cache capacity cs.lg cs.os dynamic fragmentation gpu inference llm llms management memory prior systems type virtual
More from arxiv.org / cs.LG updates on arXiv.org
Efficient Data-Driven MPC for Demand Response of Commercial Buildings
2 days, 22 hours ago |
arxiv.org
Testing the Segment Anything Model on radiology data
2 days, 22 hours ago |
arxiv.org
Calorimeter shower superresolution
2 days, 22 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US