Abstract
Generative Recommender (GR) inference places embedding hot caches (EMB) and KV caches in direct competition for limited GPU HBM: allocating more memory to one improves its efficiency but degrades the other. Existing systems optimize them in isolation, overlooking that the optimal EMB-KV allocation ratio can shift by up to 0.35 across workload regimes, leaving 20-30% latency improvement unrealized. While online reallocation is required to close this gap, naive approaches introduce H2D refill traffic on the critical path, causing P99 SLO violations. To address this, we present HELM, which jointly manages HBM allocation and request routing at runtime through two key components: (1) Adaptive Memory Allocation, a three-layer PPO-based controller (frozen base policy, online residual adapter, and burst-aware recovery controller) that achieves 32μs decision latency while staying within 0.024-0.029 of the offline-optimal ratio; and (2) EMB-KV-Aware Scheduling, which routes requests by jointly considering KV residency, embedding locality, and node load to avoid routing inefficiencies under heterogeneous allocations. Evaluations on three production-scale datasets over a 32-node A100 cluster show that HELM reduces P99 latency by 24-38% over the best static policy and achieves 93.5-99.6% SLO satisfaction across Steady, Trend, and Burst workloads, significantly outperforming state-of-the-art baselines without sacrificing throughput.
Explore similar work
Apr 24, 2026cs.LG
Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-request Key-Value (KV) cache reuse presents a significant optimization opportunity, the massive scale of individual user states creates a storage explosion that far exceeds physical GPU limits. We propose MTServe, a hierarchical cache management system that virtualizes GPU memory by leveraging host RAM as a scalable backup store. To bridge the I/O gap between tiers, MTServe introduces a suite of system-level optimizations, including a hybrid storage layout, an asynchronous data transfer pipeline, and a locality-driven replacement policy. On both public and production datasets, MTServe delivers up to 3.1* speedup while maintaining near-perfect hit ratios (>98.5%).
Xin Wang, Chi Ma, Shaobin Chen +14
Dec 12, 2025cs.LG
Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based architectures, GR's workload differs markedly from that of LLM serving. GR typically processes long prompt while producing short, fixed-length outputs, yet the computational cost of each decode phase is especially high due to the large beam width. Furthermore, since the beam search involves a vast item space, the sorting overhead becomes particularly time-consuming. We propose xGR, a GR-oriented serving system that meets strict low-latency requirements under high-concurrency scenarios. First, xGR unifies the processing of prefill and decode phases through staged computation and separated KV cache. Second, xGR enables early sorting termination and mask-based item filtering with data structure reuse. Third, xGR reconstructs the overall pipeline to exploit multi-level overlap and multi-stream parallelism. The experiments on real-world datasets demonstrate that xGR achieves at least 2.89x throughput compared to the state-of-the-art baseline under strict latency constraints.
Qingxiao Sun, Tongxuan Liu, Shen Zhang +13
Sep 14, 2026cs.AI
Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or repeatedly replay shared history, incurring substantial memory and traffic overhead. To address this, we present OneLA, a linear-attention decoding framework that exploits the shared prompt and short divergent suffixes of GR workloads. Specifically, OneLA represents all beam states using a single shared prompt-derived state and compact, append-only records of their divergent transitions. Using this representation, OneLA computes only the state information required at each decoding step, without reconstructing a full recurrent state for every beam. Furthermore, OneLA uses a lightweight ancestry index to track the transition records that make up each beam's history, allowing beams to be updated without moving or copying existing records. A fused GPU kernel further reuses the shared state across beams. Our analysis shows that OneLA achieves 1.54-2.46x end-to-end decode speedups while substantially reducing recurrent-state memory use and data movement.
Xiangrui Yang, Cheng Peng, Yunfeng Zhao +9