#Inference Acceleration
Latest news articles tagged with "Inference Acceleration". Follow the timeline of events, related topics, and entities.
Articles (2)
-
🇺🇸 Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability
[USA]
arXiv:2603.12038v1 Announce Type: cross Abstract: Long-context autoregressive decoding remains expensive because each decoding step must repeatedly process a growing history. We observe a consistent ...
Related: #Computational Efficiency -
🇺🇸 AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
[USA]
arXiv:2603.11873v1 Announce Type: new Abstract: The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for ...
Related: #AI Optimization
About the topic: Inference Acceleration
The topic "Inference Acceleration" aggregates 2+ news articles from various countries.