all AI news
Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
March 15, 2024, 4:41 a.m. | Muhammad Adnan, Akhil Arunkumar, Gaurav Jain, Prashant J. Nair, Ilya Soloveychik, Purushotham Kamath
cs.LG updates on arXiv.org arxiv.org
Abstract: Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which constitutes the majority of the computational workload, primarily entails vector-matrix multiplications and interactions with the Key-Value (KV) Cache. This phase is constrained by memory bandwidth due to the overhead of transferring weights and KV cache values from the memory system to the computing units. …
abstract architecture arxiv cache computational cs.ai cs.ar cs.lg generative inference key language language models large language large language models llms matrix process processing prompt through token tokens transformers type vector
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US