inference efficiency

Boosted Dynamic Neural Networks AAAI 2023 Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models EMNLP 2023 Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models NeurIPS 2023 Compressing Context to Enhance Inference Efficiency of Large Language Models EMNLP 2023 Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference NeurIPS 2023 Cost-effective Artificial Neural Networks IJCAI 2023 Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time ICML 2023 DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models ACL 2023 Dynamic and Efficient Inference for Text Generation via BERT Family ACL 2023 Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers NeurIPS 2023 Dynamic Transformers Provide a False Sense of Efficiency ACL 2023 Exploring the Relative Value of Collaborative Optimisation Pathways (Student Abstract) AAAI 2023 Gatekeeper to save COGS and improve efficiency of Text Prediction EMNLP 2023 GWQ: Group-Wise Quantization Framework for Neural Networks ACML 2023 H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models NeurIPS 2023 HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023 INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation ACL 2023 Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions NeurIPS 2023 MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions ICLR 2023 Not All Neighbors Matter: Point Distribution-Aware Pruning for 3D Point Cloud AAAI 2023 Open-ended Long Text Generation via Masked Language Modeling ACL 2023 Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference AAAI 2023 REx: Data-Free Residual Quantization Error Expansion NeurIPS 2023 Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time NeurIPS 2023 Serving Graph Compression for Graph Neural Networks ICLR 2023