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: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.
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:2610.33006v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) impose substantial computation and memory costs as context sizes increase, motivating methods that compr...
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
The paper surveys memory‑centric compression techniques for large language models, framing long‑context handling as a memory‑management problem. It distinguishes compute‑active memory from compute‑inactive memory, and models operations such as writing, offloading, recall, and forgetting as state transitions within an information lifecycle. The authors propose a unified cost model and argue that future research should focus on dynamic, lifecycle‑aware memory management rather than static compression.
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.
arXiv:2608. 02560v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache that grows with each generated token.
arXiv:2607. 14327v1 Announce Type: cross Abstract: Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds.
arXiv:2607. 06519v1 Announce Type: new Abstract: Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning.
arXiv:2608. 16844v1 Announce Type: cross Abstract: The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on memory-based models that can compress context into a compact state.
arXiv:2611.05386v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly deployed on consumer-grade hardware, yet their ability to preserve information across progressively longe...