arXiv subjects

Yuwei An

Publications and source records attributed to Yuwei An.

8 recordsLinked to original sources

arXiv2025

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across different queries and inference engines. Our real-world usage statistics confirm this trend: over time, the total KV cache stored by users has grown rapidly, far exceeding the capacity of GPU memory. Despite this need, there lacks an efficient solution for offloading and transferring KV caches. We present LMCACHE, the first and so far the most efficient open-source KV caching solution, which extracts and stores KV caches generated by modern LLM engines (vLLM and SGLang) out of the GPU memory and shares them across engines and queries. LMCACHE supports both cache offloading (prefix reuse across queries) and prefill-decode (PD) disaggregation (cross-engine/GPU cache transfer). LMCACHE's high performance and wide adoption stem from the following contributions: (1) highly optimized KV cache data movement powered by batched data movement operations, compute and I/O pipelining; (2) a modular KV cache connector component, decoupling LMCACHE from the rapid evolution of inference engines; (3) a first-class control API for flexible cache orchestration across GPU, CPU, storage, and network layers. Our evaluation shows that combining LMCACHE with vLLM achieves up to 15x improvement in throughput across workloads such as multi-round question answering and document analysis. Large-scale adoption of LMCACHE in enterprise settings provides us valuable insights, for example, fetching KV cache from remote storage has unsurprisingly benefits to prefill delay, and that context truncation, which is a widely applied technique in industry, can greatly reduce prefix cache hit ratio by half. The source code of LMCACHE is at: https://github.com/LMCache/LMCache.

cs.LG↗

arXiv2025

Strata: Hierarchical Context Caching for Long Context Language Model Serving

Large Language Models (LLMs) with expanding context windows face significant performance hurdles. While caching key-value (KV) states is critical for avoiding redundant computation, the storage footprint of long-context caches quickly exceeds GPU memory capacity, forcing production systems to adopt hierarchical caching across memory hierarchies. However, transferring large cached contexts back to the GPU introduces severe performance bottlenecks: fragmented I/O from paged layouts prevents full bandwidth utilization, and existing schedulers fail to account for cache-loading delays, leaving systems loading-bound rather than compute-bound. We present Strata, a hierarchical context caching framework designed for efficient long context LLM serving. Strata introduces GPU-assisted I/O to combat KV cache fragmentation, decoupling GPU and CPU memory layouts and employs cache-aware request scheduling to balance compute with I/O latency and overlapping unavoidable stalls with complementary tasks. Built on SGLang and deployed in production, Strata achieves up to 5x lower Time-To-First-Token (TTFT) compared to vLLM + LMCache and 3.75x speedup over NVIDIA TensorRT-LLM on long-context benchmarks, without degrading short-context performance.

cs.DC↗

arXiv2025

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

Autoregressive Large Language Models (AR-LLMs) frequently exhibit implicit parallelism in sequential generation. Inspired by this, we introduce Multiverse, a new generative model that enables natively parallel generation. Multiverse internalizes a MapReduce paradigm, generating automatically through three stages: (i) a Map stage for adaptive task decomposition, (ii) a Process stage for parallel subtask execution, and (iii) a Reduce stage for lossless result synthesis. Next, we build a real-world Multiverse reasoning model with co-design of data, algorithm, and system, enabling rapid and seamless transfer from frontier AR-LLMs. For data creation, we develop Multiverse Curator, an automated LLM-assisted pipeline that transforms sequential reasoning chains into structured training data, avoiding costly human annotations. Algorithmically, we design Multiverse Attention to separate parallel reasoning steps while keeping compatibility with causal attention for efficient training. Systematically, we implement Multiverse Engine to support parallel inference. It features a dedicated interpreter that dynamically switches between sequential and parallel generation, triggered directly by the model. After a 3-hour fine-tuning with 1K examples, our Multiverse-32B stands as the only open-sourced non-AR model achieving performance on par with leading AR-LLMs of the same scale, evidenced by AIME24 & 25 scores of 54% and 46%, respectively. Moreover, our budget control experiments show that Multiverse-32B exhibits superior scaling, outperforming AR-LLMs by 1.87% on average using the same context length. Such scaling further leads to practical efficiency gains, achieving up to 2x speedup across varying batch sizes. We have open-sourced the entire Multiverse ecosystem, including data, model weights, engine, as well as complete data curation prompts and detailed training and evaluation recipes.

cs.LG↗

arXiv2025

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics

Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from domain specifics to examine reasoning as a capability in and of itself. We contribute a novel type of benchmark evaluating the inductive reasoning capabilities of LLMs that is inspired by the forward reconstruction task from historical linguistics but is formulated in an extremely simple, general way (in the form of Programming by Examples). The task involves generating a cascade of simple string rewrite programs to transform a given list of input strings into a list of desired output strings. We present a fully automated pipeline that programmatically generates problems of this type with controllable difficulty, enabling scalable evaluation of reasoning models while avoiding contamination. Using this approach, we construct two benchmarks: PBEBench-Lite, which efficiently stratifies models of varying capabilities, and PBEBench, which requires models to induce programs similar in complexity to those constructed by historical linguists. Our experiments reveal a substantial performance gap between models that leverage test-time compute or LCoT (long chain-of-thought) reasoning and those that do not. Moreover, although recent models show promise, the solve rate for both of them drops below 5% for hard instances of the PBEBench dataset (ground truth cascade lengths of 20 and 30, respectively), falling well short of realistic historical linguistics requirements even with computationally expensive, popular scaling techniques from the PBE and reasoning literature. Additionally, we also study the effectiveness of different scaling strategies and the impact of various hyperparameters on the difficulty of the generated data using gpt-oss-120b, the best-performing open-source model.

cs.CL↗

arXiv2025

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Analysis of production traces reveals a dynamic bursty-group pattern in which sets of models become active together and shift over time; existing space- and time-sharing approaches lack principled mechanisms to adapt to this variability, forcing trade-offs between SLO adherence and efficiency. We observe that elastic memory allocation can unify spatial and temporal sharing. Based on this insight, we have developed Prism, a memory-centric LLM co-serving framework that applies memory ballooning to reclaim memory across models and support both forms of sharing under a single scheme. Prism's balloon driver, referred to as kvcached, has been open-sourced at https://github.com/ovg-project/kvcached, and deployed in production environments across 10K+ GPUs.

cs.DC↗

arXiv2025

HyperRAG: Enhancing Quality-Efficiency Tradeoffs in Retrieval-Augmented Generation with Reranker KV-Cache Reuse

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the performance of large language models (LLMs) by integrating external knowledge into the generation process. A key component of RAG pipelines is the reranker, which selects the most relevant documents from a pool of retrieved candidates and significantly improves the quality of the generated responses. While rerankers refine the selection of retrieved documents in RAG pipelines, they introduce computational challenges that hinder high throughput and low latency. To address this problem, we propose HyperRAG, a system that optimizes the trade-off between quality and efficiency in RAG pipelines by leveraging KV-cache reuse for efficient reranker inference. By reusing document-side KV-cache, HyperRAG achieves both high-quality generation and system-level efficiency. To fully realize the benefits of KV-cache reuse, HyperRAG incorporates a range of system-level optimizations designed to enhance efficiency and scalability. Experiments show that HyperRAG achieves a 2 - 3 throughput improvement with decoder-only rerankers while also delivering higher downstream performance compared with traditional RAG service.

cs.CL↗

arXiv2024

OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining

With the rapid proliferation of scientific literature, versatile academic knowledge services increasingly rely on comprehensive academic graph mining. Despite the availability of public academic graphs, benchmarks, and datasets, these resources often fall short in multi-aspect and fine-grained annotations, are constrained to specific task types and domains, or lack underlying real academic graphs. In this paper, we present OAG-Bench, a comprehensive, multi-aspect, and fine-grained human-curated benchmark based on the Open Academic Graph (OAG). OAG-Bench covers 10 tasks, 20 datasets, 70+ baselines, and 120+ experimental results to date. We propose new data annotation strategies for certain tasks and offer a suite of data pre-processing codes, algorithm implementations, and standardized evaluation protocols to facilitate academic graph mining. Extensive experiments reveal that even advanced algorithms like large language models (LLMs) encounter difficulties in addressing key challenges in certain tasks, such as paper source tracing and scholar profiling. We also introduce the Open Academic Graph Challenge (OAG-Challenge) to encourage community input and sharing. We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field. OAG-Bench is accessible at https://www.aminer.cn/data/.

cs.DL↗

arXiv2023

Controllable Mesh Generation Through Sparse Latent Point Diffusion Models

Mesh generation is of great value in various applications involving computer graphics and virtual content, yet designing generative models for meshes is challenging due to their irregular data structure and inconsistent topology of meshes in the same category. In this work, we design a novel sparse latent point diffusion model for mesh generation. Our key insight is to regard point clouds as an intermediate representation of meshes, and model the distribution of point clouds instead. While meshes can be generated from point clouds via techniques like Shape as Points (SAP), the challenges of directly generating meshes can be effectively avoided. To boost the efficiency and controllability of our mesh generation method, we propose to further encode point clouds to a set of sparse latent points with point-wise semantic meaningful features, where two DDPMs are trained in the space of sparse latent points to respectively model the distribution of the latent point positions and features at these latent points. We find that sampling in this latent space is faster than directly sampling dense point clouds. Moreover, the sparse latent points also enable us to explicitly control both the overall structures and local details of the generated meshes. Extensive experiments are conducted on the ShapeNet dataset, where our proposed sparse latent point diffusion model achieves superior performance in terms of generation quality and controllability when compared to existing methods.

cs.CV↗