Search Results for author:
Found 4 papers, 3 papers with code
Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference
Unlike previous methods, our solution can be directly applied to pre-trained MoE models without any fine-tuning or accuracy degradation.
Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference
Inference on these models, by design, harnesses a temporal dependency, where the current token's probability distribution is conditioned on preceding tokens.
SOFT: Softmax-free Transformer with Linear Complexity
Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.
Single Pixel Reconstruction for One-stage Instance Segmentation
In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
