inference acceleration

Speculative Sampling via Exponential Races ACL 2025 Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025 Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications ACL 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming AAAI 2025 Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More EMNLP 2025 SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration ICLR 2025 TCFG: Truncated Classifier-Free Guidance for Efficient and Scalable Text-to-Image Acceleration ICCV 2025 The Impact of Inference Acceleration on Bias of LLMs NAACL 2025 Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model CVPR 2025 Towards Codec-LM Co-design for Neural Codec Language Models NAACL 2025 Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025 TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text EMNLP 2025 Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling ACL 2025 Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language Models EMNLP 2025 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models EMNLP 2025 VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration ICLR 2025 Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models EMNLP 2025 When Attention Sink Emerges in Language Models: An Empirical View ICLR 2025 WINS: Winograd Structured Pruning for Fast Winograd Convolution ICCV 2025 XAttention: Block Sparse Attention with Antidiagonal Scoring ICML 2025 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution NeurIPS 2024 Accelerating Blockwise Parallel Language Models with Draft Refinement NeurIPS 2024 AFPQ: Asymmetric Floating Point Quantization for LLMs ACL 2024 AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising NeurIPS 2024