attention computation

SCOPE: Boosting LLM Efficiency with Scoped Position Encoding ACL 2026 SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026 Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning ICCV 2025 SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ICML 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection EMNLP 2025 VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs EMNLP 2025 An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models ECCV 2024 InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management OSDI 2024 NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention NeurIPS 2024 Fast Attention Requires Bounded Entries NeurIPS 2023 Treeformer: Dense Gradient Trees for Efficient Attention Computation ICLR 2023 The Devil in Linear Transformer EMNLP 2022 Grounding Spatio-Temporal Language with Transformers NeurIPS 2021