GRACE: Generative Recommender Acceleration Engine for Real-Time Ads Retrieval

• URL: http://arxiv.org/abs/2608.00938v2
• Date: Tue, 04 Aug 2026 15:35:10 GMT
• Title: GRACE: Generative Recommender Acceleration Engine for Real-Time Ads Retrieval
• Abstract summary: This paper presents GRACE, a serving system for ads generative retrieval.<n>For eligibility, GRACE introduces Generative Target Matching (GTM), which extends catalog-valid constrained decoding.<n>For compute-cost and latency, GRACE targets encoder-decoder Transformers, which are more lightweight than LLMs.
• Score: 15.73766250149643
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Productionizing generative recommenders for high-volume, real-time ads retrieval creates two serving challenges: eligibility, ensuring that each generated ad is eligible for the request under the advertiser's audience targeting rules, and compute, which requires meeting strict latency and GPU cost requirements while remaining capable of generating thousands of ads per request with wide-beam decoding. This paper presents GRACE, a serving system for ads generative retrieval that addresses both challenges. For eligibility, GRACE introduces Generative Target Matching (GTM), which extends catalog-valid constrained decoding with personalized filtering over Semantic ID (SID) prefixes using bitmask and Bloom filter matchers derived from targeting rules. SID-level GTM improves final ad-level target matching pass rate from 23.55% to 40.42% over constrained decoding alone. For compute-cost and latency, GRACE targets encoder-decoder Transformers, which are more lightweight than LLMs. It redesigns the decoder around the wide-beam, short-sequence regime, covering attention kernels, KV cache, and beam search optimizations. On NVIDIA GH200, compared with the faster of FlashAttention-2 and FlashAttention-3 baselines, GRACE improves cross-attention latency by 68.0 times and self-attention latency by 23.4-25.8 times across decode steps. Together, these changes reduce decoder latency by 11.1 times, keeping ads generative retrieval within latency and compute requirements.

Related papers

• Long-History User Transformers for Real-Time Ad Ranking [0.027185251060695432]
  We describe how a production advertising system resolves this conflict by decoupling history encoding from real-time inference.<n>A high-capacity offline transformer asynchronously encodes the user's full cross-surface interaction history into a compact representation cached in a feature store.<n>In production A/B experiments, the system improves the primary ranking metric by +2.77% in search advertising and +2.1% on the Yandex Advertising Network, with revenue gains of +2.26% and +0.43% respectively.
  arXiv  Detail & Related papers  (2026-07-15T19:51:16Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• Tiny Inference-Time Scaling with Latent Verifiers [56.696619768584675]
  Verifier on Hidden States ( VHS) operates on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators.<n> VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost.<n> VHS achieves a +2.7% improvement on GenEval at the same inference-time budget.
  arXiv  Detail & Related papers  (2026-03-23T19:00:02Z)
• Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs [57.69190972274813]
  Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models.<n>ExistingDLLMs are plagued by a severe quality-speed trade-off, where faster parallel decoding leads to significant performance degradation.<n>We introduce Wide-In, Narrow-Out (WINO), a training-free decoding algorithm that enables revokable decoding inDLLMs.
  arXiv  Detail & Related papers  (2025-07-24T16:51:33Z)
• FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge [60.000984252907195]
  Auto-regressive (AR) models have recently shown promise in visual generation tasks due to their superior sampling efficiency.<n>Video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase.<n>We propose the textbfFastCar framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy.
  arXiv  Detail & Related papers  (2025-05-17T05:00:39Z)
• Efficient Inference for Large Language Model-based Generative Recommendation [78.38878421030522]
  Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly.<n>Applying Speculative Decoding (SD) to generative recommendation presents unique challenges due to the requirement of generating top-K items.<n>We propose an alignment framework named AtSpeed, which presents the AtSpeed-S optimization objective for top-K alignment under the strict top-K verification.
  arXiv  Detail & Related papers  (2024-10-07T16:23:36Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)
• Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR [44.229256049718316]
  Streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. In these models, the decisions to generate tokens are delayed compared to the actual acoustic boundaries since their unidirectional encoders lack future information. We propose several strategies during training by leveraging external hard alignments extracted from the hybrid model. Experiments on the Cortana voice search task demonstrate that our proposed methods can significantly reduce the latency, and even improve the recognition accuracy in certain cases on the decoder side.
  arXiv  Detail & Related papers  (2020-04-10T12:24:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.