arXiv:2602. 22647v2 Announce Type: replace-cross Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation.
arXiv:2607. 10044v1 Announce Type: new Abstract: Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs.
Orthrus is a serving system that performs heterogeneous batching of embedding and generative models within a single inference loop. It uses chunked embedding with incremental pooling and workload‑aware batch composition to unify conflicting computational patterns. Experiments on four A100 GPUs show that Orthrus improves throughput by 1.28×–4.52× and reduces p99 latency by up to 55.8% compared to baseline deployments.
arXiv:2609.05760v1 Announce Type: cross Abstract: We present RAGMark, a modular benchmarking framework for advanced Retrieval-Augmented Generation (RAG) systems targeting small-scale multi-GPU enviro...
arXiv:2601. 07048v5 Announce Type: replace-cross Abstract: Approximate nearest neighbor search (ANNS) is a core problem in machine learning and information retrieval applications.
arXiv:2609.21281v1 Announce Type: cross Abstract: Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, exp...
arXiv:2603. 29002v3 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning.
Celty introduces a co-designed sparse format, GPU kernel, and SIMT microarchitecture to efficiently handle Sparse Matrix‑Sparse Vector (SpMSpV) workloads in large language model inference. Its Run‑Length Compressed CSC (RLC‑CSC) format allows vectorized loading of compressed weight columns and skips memory accesses by exploiting both weight pruning and activation sparsity. The Celty Sparse SIMT Core adds a pipelined RLC decoder that eliminates software index reconstruction and uses local registers for conflict‑free accumulation, achieving up to 5.3× speedup over cuBLAS at 70% dual‑sparsity.
arXiv:2608. 01536v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weight or activation-and optimizes for batched multi-user inference.
DeGRe is a dense‑supervised generative reranking framework designed to improve multi‑stage recommender systems by addressing label bias and credit assignment issues. It uses an offline Lookahead Evaluator with beam search to generate dense supervision signals, which are distilled into a lightweight Online Generator that can perform efficient greedy decoding at inference time. Experiments show that DeGRe outperforms baselines on public benchmarks and industrial datasets, and it has been successfully deployed on Taobao Flash Shopping to enhance online recommendations.
The paper "LLM Inference in a Flash!" proposes an integer‑only quantization scheme and a dictionary‑based KV cache compression technique to enable large language model inference on compute‑in‑flash (CIF) devices. By eliminating floating‑point operations and reducing KV cache traffic through sparse dictionary coding, the authors achieve minimal accuracy loss while cutting dynamic KV cache traffic by 15× on Llama‑3.1‑8B and Qwen‑2.5‑7B models.
BeaconKV is a training‑free key‑value cache compression technique for Large Reasoning Models that uses beacon queries—compact representatives of query clusters—to predict which KV pairs will be revisited during long‑horizon reasoning. By focusing on Thought Revisiting Tokens that re‑attend distant context, BeaconKV reduces memory usage up to 5.8× and improves throughput by over 4.3× while largely preserving cache accuracy across multiple open‑source LRMs and reasoning benchmarks.
The paper presents a budget‑aware compression pipeline for deploying 70B‑parameter language models on a single NVIDIA GPU. It examines how pruning, quantization, and KV‑cache compression interact, showing that layer‑wise pruning improves weight quantization robustness and that KV‑cache sparsification complements INT8 KV quantization without harming decoding speed. Using these insights, the authors compressed a 70B model to ~33 GB, achieving ~57 tokens/s on 10k‑token prompts on an A40 while maintaining accuracy within 5% on standard benchmarks.