arXiv AI
Jun 9
End-to-End Context Compression at Scale
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
End-to-End Context Compression at Scale
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.
Related stories
arXiv Computation and Language
Sep 23
Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...
arXiv AI
5d ago
ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
arXiv:2602.08005v2 Announce Type: replace-cross Abstract: Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computati...
arXiv AI
Jul 8
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression
arXiv:2607. 06523v1 Announce Type: new Abstract: Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation.
arXiv AI
6d ago
KV-Kaizen: Learning Context-Adaptive Cache Compression Choices
arXiv:2609.37988v1 Announce Type: new Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This i...
arXiv AI
Jun 24
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.
Hugging Face Trending Papers
Aug 24
ProxyFormer: A Dual-Stream Proxy Architecture for Ultra-Long Context and High-Resolution Generation
The quadratic growth of attention computation and key-value (KV) cache with respect to sequence length is a central bottleneck for ultra-long-context language models and high-resolution generative mod...
arXiv AI
Jul 31
ARC-Encoder: learning compressed text representations for large language models
arXiv:2510. 20535v2 Announce Type: replace-cross Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs.
Hugging Face Trending Papers
Jun 23
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
arXiv Machine Learning
Sep 21
Elastic Threshold Attention: Learned Contextual Sparsity for Long-Context Decoding
Elastic Threshold Attention (ETA) is a trainable attention mechanism that dynamically predicts contextual thresholds from query representations, enabling selective pruning of KV cache tokens during long‑context decoding. By multiplicatively suppressing sub‑threshold logits during training, ETA avoids representation collapse and eliminates localized attention sinks, allowing a 1.45B model to match dense attention performance at roughly 85% training sparsity and 38% active decode density. At inference, a custom Triton kernel achieves up to 2.5× faster decoding on sequences up to 512K tokens, and an offline calibration step can further reduce compute by 27% by freezing per‑head thresholds.
arXiv Machine Learning
4d ago
PatchKV: Weight-Space Compensation of KV Cache
arXiv:2609.39329v1 Announce Type: new Abstract: Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compressi...
arXiv Machine Learning
Aug 26
PuzzleKV: Page-Wise Low-Rank Decomposition for KV Cache Compression
arXiv:2608.23843v1 Announce Type: new Abstract: Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compressio...