arXiv:2606. 24506v1 Announce Type: cross Abstract: Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold.
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.
arXiv:2606. 06256v1 Announce Type: new Abstract: As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure.
arXiv:2606. 02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation.
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.
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: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.
arXiv:2606. 06302v2 Announce Type: replace Abstract: Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput.
arXiv:2610.19822v1 Announce Type: cross Abstract: LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct wei...
The paper introduces Group-Query Latent Attention (GQLA), a variant of Multi-head Latent Attention that shares group‑sharded up‑projections to enable a joint latent representation and a shardable expanded cache. GQLA supports both MQA‑absorb and GQA execution using the same weights and existing kernels, and roofline analysis shows how absorption trades traffic for computation while GQA shards KV groups. Experiments on DeepSeek‑V3.1‑Base and other models demonstrate that GQLA achieves comparable training losses to MLA, maintains high accuracy after checkpoint conversion, and improves output throughput by up to 35% on eight H20‑3e GPUs, while also allowing larger batch sizes due to a smaller per‑rank cache.
DualPace is an LLM serving runtime that decouples scheduling between a GPU engine and an AMX‑enabled CPU engine, allowing the CPU to independently batch and advance decodes while still cooperating with the GPU for dense stages. This design expands key‑value cache capacity into host memory and reduces bursty CPU progress, leading to significant throughput gains—up to 43.2 % over NEO and 90.6 % over vLLM—without increasing latency. The system also maintains low time‑to‑first‑token and supports higher request rates at comparable tail latency.
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.