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: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. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
arXiv:2608.00311v2 Announce Type: replace Abstract: Long-context inference with large language models (LLMs) is costly: self-attention during prefill scales quadratically with sequence length, and th...
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: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: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.
MILO is a compression framework that reduces the key-value cache memory used in many-shot in-context learning by applying block-wise low-rank compression. It dynamically allocates rank budgets to blocks based on information entropy, preserving important information while aggressively compressing redundant parts. Experiments on Qwen2.5 models show up to a 50% reduction in KV cache memory and a 1.8× throughput improvement with negligible performance loss on classification and reasoning tasks.
The paper introduces a long‑context recall technique that keeps GPU memory usage nearly constant regardless of context length, without requiring additional training. It reconstructs facts by leveraging residual vectors stored in the LLM’s feed‑forward layers, enabling deterministic retrieval of query‑relevant information without accessing the original document. Experiments demonstrate the method can answer single‑fact questions in two‑million‑token stories, outperforming prior approaches.
arXiv:2608. 12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length.
arXiv:2607. 01237v1 Announce Type: cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput.
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:2607. 01237v2 Announce Type: replace-cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput.