inference optimization

Token Knowledge: A New Perspective For Knowledge in Large Language Models EMNLP 2025 Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem? ACL 2025 TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection EMNLP 2025 TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model CVPR 2025 Towards Economical Inference: Enabling DeepSeek’s Multi-Head Latent Attention in Any Transformer-based LLMs ACL 2025 Treasures in Discarded Weights for LLM Quantization AAAI 2025 TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text EMNLP 2025 Unleashing Vecset Diffusion Model for Fast Shape Generation ICCV 2025 Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning ACL 2025 VisionZip: Longer is Better but Not Necessary in Vision Language Models CVPR 2025 VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service ACL 2025 VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis ICLR 2025 Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design NeurIPS 2024 Adaptive Deep Neural Network Inference Optimization With EENet WACV 2024 Approximate Caching for Efficiently Serving Text-to-Image Diffusion Models NSDI 2024 Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems NeurIPS 2024 A Thorough Examination of Decoding Methods in the Era of LLMs EMNLP 2024 Cascade Speculative Drafting for Even Faster LLM Inference NeurIPS 2024 CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification EMNLP 2024 ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition ACL 2024 Compressed Context Memory for Online Language Model Interaction ICLR 2024 Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification AISTATS 2024 DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models EMNLP 2024 EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees EMNLP 2024 Efficient LLM Scheduling by Learning to Rank NeurIPS 2024