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. 27090v1 Announce Type: cross Abstract: Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests.
Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests. Production memory systems (e.
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...
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value c...
arXiv:2607. 07388v1 Announce Type: cross Abstract: Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion costly through pretraining, fine-tuning, retrieval augmentation, or longer contexts.
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.
arXiv:2606. 28876v1 Announce Type: cross Abstract: Long-context language models often conflate two different goals: compressing history into an efficient state, and maintaining reliable long-term memory.
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:2601. 07372v2 Announce Type: replace-cross Abstract: While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation.
arXiv:2606. 29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.
arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...
GroupKV is a lightweight hierarchical KV cache management system designed for long‑context diffusion large language model (dLLM) inference. It partitions the context into contiguous groups and uses coarse‑to‑fine sparse selection, cross‑layer consistency for predictive prefetching, and a staleness correction mechanism to keep the cache coherent amid dynamic KV updates. The approach also incorporates streaming prefill to lower peak memory usage, achieving up to 48× longer serviceable context, 3.73× faster inference in offload‑based settings, and competitive task accuracy.