cs.LGNov 17, 2026

Optimize the Cob, Then the Kernel: Optimizing Beam Search for Generative Recommendation Inference

Authors: Shing Wai Pun, Kai Wu, Pengfei Xia, Hui Zang, Wei Guo, Yong Liu

Organizations: Huawei Technologies Co., Ltd.

Abstract

Generative recommendation (GR) inference differs substantially from conventional LLM serving, featuring long input sequences, wide beam search, and only a few fixed output tokens. Existing LLM serving engines such as vLLM process beams as batched independent sequences, causing redundant KV cache accesses over the shared prompt prefix. Furthermore, vLLM executes each beam search generation step as a separate engine invocation, incurring host-side beam processing overhead between decoding steps and substantial runtime KV block management in PagedAttention. Using Tree Attention, we concatenate beams along the sequence dimension to eliminate redundant KV accesses, and further optimize execution through pre-generated partial-attention masks, static KV cache allocation, loop-unrolled generation dispatch, TorchAir graph compilation, automatic operator fusion, and vocabulary-constrained decoding. Without the use of custom kernels, our approach reduces end-to-end latency by up to 25x over vLLM on Ascend NPUs, and achieves generation latency comparable to a SOTA solution using custom kernels, showing that the generation pipeline should be optimized holistically before resorting to custom kernel development.

Figures & tables

Explore similar work

Sep 11, 2026

OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation

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.
Dec 12, 2025

xGR: Efficient Generative Recommendation Serving at Scale

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.
Sep 29, 2026

Provable Test-Time Scaling for Beam Search in LLM Reasoning

Beam-search-based test-time methods provide an effective way to improve large language model (LLM) performance on long-horizon generation by pruning invalid reasoning paths early, leading to significantly improved reasoning efficiency and more favorable test-time cost scaling. Despite strong empirical success, the theoretical understanding of beam search remains limited. In this paper, we study the test-time compute guarantee of the commonly used beam search framework that uses the model's internal log-likelihood for intermediate scoring, while relying on an external reward model only after a complete response is generated. We first establish a lower bound for vanilla beam search, showing that at least Ω(C⋆(x)2)Ω(C^\star(x)^2) samples are required for the optimal response to survive, where C⋆(x)C^\star(x) is the token-level coverage coefficient for prompt xx. This motivates our modified confidence-filtered beam search (CF-Beam), which reduces the sufficient coverage dependence from quadratic to nearly linear under prefix competitiveness, for fixed horizon, gap, and target accuracy. We then show that the regret of CF-Beam is upper-bounded by the probability of rare failure events and the reward estimation error scaled by a path-level coverage coefficient, where the rare-failure term vanishes as per-step sampling increases. Our results highlight a fundamental advantage of beam search over sequence-level inference methods such as Best-of-N and Best-of-Majority. While the guarantees of these approaches typically involve coverage coefficients that grow exponentially with the horizon LL, CF-Beam controls the dominant search-induced term through a token-level coverage coefficient that scales polynomially with LL. Our numerical experiments further confirm that beam search is more robust on hard instances and under increasing reasoning horizons.