#AI acceleration
Latest news articles tagged with "AI acceleration". Follow the timeline of events, related topics, and entities.
Articles (3)
-
πΊπΈ KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
[USA]
arXiv:2602.20217v1 Announce Type: cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on s...
Related: #Computational efficiency, #Model optimization, #Hardware adaptation -
πΊπΈ LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration
[USA]
arXiv:2602.20497v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transform...
Related: #Diffusion models, #Computer vision -
πΊπΈ TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design
[USA]
arXiv:2602.12962v1 Announce Type: cross Abstract: Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-con...
Related: #Hardware-software co-design, #Resource optimization