Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG cache fusion reduces this cost by reusing precomputed key-value (KV) caches for retrieved chunks and selectively recomputing tokens under the current prompt.
arXiv:2606. 05875v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost.
arXiv:2608. 03276v1 Announce Type: new Abstract: Long-context inference with large language models is constrained by the linear growth of the key-value cache to sequence length.
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.
The paper introduces REVA, a method for compressing retrieval-augmented generation (RAG) prompts by aggregating historical query–document–model interactions into reusable evidence views. REVA mines attention traces from the target generator, maps token-level attention to readable words, aggregates importance across repeated document accesses, and produces budget‑specific plain‑text views that maintain document order and the standard RAG interface. Experiments on four benchmarks with modern LLMs show that REVA improves generation quality by 1.0–5.8 points over existing compressors while reducing compression overhead by 5.3 to 15.6 times and adding less than 40 ms of latency.
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: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...
arXiv:2603. 05353v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts.
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:2504. 20114v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks.
CacheWeaver is a lightweight prompt‑layer technique that orders evidence for Retrieval‑Augmented Generation (RAG) to improve cache reuse in serving engines like vLLM. By maintaining a prefix tree of recently served evidence sequences and greedily placing the most reusable prefix first, it reduces median time‑to‑first‑token by 20‑33 % across three vLLM configurations without harming answer quality. The greedy policy achieves 97.5 % of the gain possible with oracle ordering, showing that most reusable prefix locality can be recovered with a simple scheduling layer.
SGD-KV is a head‑aware framework for compressing key‑value caches in large language models. It uses a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation, allowing the KV cache budget to be allocated based on each head’s summarization score. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B show state‑of‑the‑art performance on up to 1M‑token contexts while cutting KV cache memory usage by up to 75%.