inference acceleration

Speculative Contrastive Decoding ACL 2024 Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism ACL 2024 Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration NeurIPS 2024 SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform NeurIPS 2024 The Mamba in the Llama: Distilling and Accelerating Hybrid Models NeurIPS 2024 Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner CVPR 2024 UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs ACL 2024 UltraSparseBERT: 99% Conditionally Sparse Language Modelling ACL 2024 UniFL: Improve Latent Diffusion Model via Unified Feedback Learning NeurIPS 2024 Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression ACL 2024 Wino Vidi Vici: Conquering Numerical Instability of 8-Bit Winograd Convolution for Accurate Inference Acceleration on Edge WACV 2024 Accelerating Transducers through Adjacent Token Merging Interspeech 2023 Accelerating Transformer Inference for Translation via Parallel Decoding ACL 2023 Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention IJCAI 2023 Algorithm-Hardware Co-Design for Efficient Brain-Inspired Hyperdimensional Learning on Edge (Extended Abstract) IJCAI 2023 Attend, Select and Eliminate: Accelerating Multi-turn Response Selection with Dual-attention-based Content Elimination ACL 2023 DeepPCR: Parallelizing Sequential Operations in Neural Networks NeurIPS 2023 Dynamic Sparsity Is Channel-Level Sparsity Learner NeurIPS 2023 Embedding Recycling for Language Models EACL 2023 Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing EMNLP 2023 Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023 NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models EMNLP 2023 On Distillation of Guided Diffusion Models CVPR 2023 ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval ICML 2023 Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline NeurIPS 2023