conftrace_

key-value cache

55 papers

Explore in graph

Also known as

KV CACHE KV-CACHE KV

Co-occurring keywords

large language model (13587) attention mechanism (4001) model compression (3302) inference efficiency (248) kv cache (74) inference optimization (219) retrieval-augmented generation (1592) memory efficiency (261) long context (121) memory optimization (114)

Papers

TimeBill: Time-Budgeted Inference for Large Language Models AAAI 2026
RetroLM: Retrieval-Augmented KVs for Long-Context Processing AAAI 2026
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization ACL 2026
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning ACL 2026
CacheNotes: Task-Aware Key-Value Cache Compression for Reasoning-Intensive Knowledge Tasks EACL 2026
Sparse Attention Across Multiple-Context KV Cache AAAI 2026
Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving AAAI 2026
HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference ACL 2026
Lizard: An Efficient Linearization Framework for Large Language Models ACL 2026
Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models ACL 2026
Q Cache: Visual Attention Is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model AAAI 2026
Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction AAAI 2026
Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention ACL 2026
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization EMNLP 2025
CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM EMNLP 2025
ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity ICCV 2025
PRISM: Efficient Long-Range Reasoning With Short-Context LLMs EMNLP 2025
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text EMNLP 2025
Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025
Boosting Long-Context Information Seeking via Query-Guided Activation Refilling ACL 2025
EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices ACL 2025
FlashBack: Efficient Retrieval-Augmented Language Modeling for Fast Inference ACL 2025
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning ACL 2025
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs ACL 2025