arXiv:2608. 10545v1 Announce Type: cross Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node.
arXiv:2609.32259v2 Announce Type: replace Abstract: Recent multi-agent LLM systems increasingly combine heterogeneous models for specialized agent roles. However, text-based communication requires ea...
The paper introduces a cache‑aware post‑training framework for Mixture‑of‑Experts (MoE) models that jointly adapts the MoE backbone and lightweight auxiliary cache routers while keeping the native Top‑K expert‑selection rule. Two modes are proposed: Temporal Router, which predicts same‑layer reuse and retains experts for future tokens, and Spatio‑Temporal Router, which adds a Spatio Router that refines the temporal cache using the causal predecessor’s hidden state. Experiments on Qwen3 and GPT‑OSS across GSM8K, MATH, and CommonsenseQA show that Temporal Router improves cache hit rates and reduces expert‑weight traffic, while Spatio‑Temporal Router achieves the best load‑adjusted efficiency, outperforming strong prefetching baselines.
WiSP (Working‑Set Paging) is a routing‑aware expert pager that allows Mixture‑of‑Experts models to run on GPUs that cannot hold the entire expert pool by paging experts in and out of VRAM while preserving byte‑identical outputs. On a 24 GiB RTX 3090, WiSP doubles decode throughput compared to static offload when the model does not fit, and its companion policy MV‑WSA allocates VRAM between resident experts and KV cache based on marginal latency benefit, reducing end‑to‑end time by up to 1.19× without altering model outputs.
arXiv:2608. 08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging.
arXiv:2609.14507v1 Announce Type: cross Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV...
The paper investigates whether training Mixture-of-Experts (MoE) routers can improve memory‑bandwidth locality on consumer GPUs. Using a new zero‑surgery telemetry tool, the authors measure that a large Qwen3‑235B model is bottlenecked by disk‑based expert access, and that an LRU cache can serve a majority of requests. They pre‑register experiments training 137 M‑parameter MoE models with locality‑aware losses, finding that while cache misses can drop up to 60 % (99 % static‑pin hit rate), every configuration fails to meet a strict 1 % perplexity threshold, indicating a tight coupling between cache efficiency and model quality.
arXiv:2608. 16477v1 Announce Type: new Abstract: AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: the user attaches to a target base station (gNB) while the large and growing key-value (KV) cache remains at the source.
arXiv:2606. 13126v1 Announce Type: cross Abstract: Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files.
Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files. Yet, prefix caching in engines such as vLLM cannot reuse their KV entries unless they share identical prefixes with another request, while Position-Independent Caching (PIC) implementations within production-grade inference servers typically either require substantial server code changes or keep KV state outside the server, incurring host-to-device transfer overhead.
CacheBridge is a method for efficiently transferring key‑value (KV) caches between large language models (LLMs) in a multi‑model system. It replaces the full‑head mapping approach by matching each target KV head to a single source head, weighting reconstruction errors by causal attention sensitivity, and building weighted sufficient statistics with a fused GPU kernel. The technique achieves comparable or better accuracy to full‑head mapping while reducing mapper storage by up to eight‑fold, accelerating application by up to three‑times, and cutting construction time dramatically.
A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We s...
arXiv:2609.17109v1 Announce Type: new Abstract: A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefi...