vCache: Verified Semantic Prompt Caching

• URL: http://arxiv.org/abs/2502.03771v3
• Date: Tue, 27 May 2025 04:15:22 GMT
• Title: vCache: Verified Semantic Prompt Caching
• Authors: Luis Gaspar Schroeder, Aditya Desai, Alejandro Cuadron, Kyle Chu, Shu Liu, Mark Zhao, Stephan Krusche, Alfons Kemper, Matei Zaharia, Joseph E. Gonzalez,
• Abstract summary: This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
• Score: 75.87215136638828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic caches return cached LLM-generated responses for semantically similar prompts to reduce inference latency and cost. They embed cached prompts and store them alongside their response in a vector database. Embedding similarity metrics assign a numerical score to quantify the similarity between a request and its nearest neighbor prompt from the cache. Existing systems use the same static similarity threshold across all requests to determine whether two prompts can share similar responses. However, we observe that static thresholds do not give formal correctness guarantees, can result in unexpected error rates, and lead to suboptimal cache hit rates. This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees. It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training. Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines. We release the vCache implementation and benchmarks to support future research.

Related papers

• MagCache: Fast Video Generation with Magnitude-Aware Cache [91.51242917160373]
  We introduce a novel and robust discovery: a unified magnitude law observed across different models and prompts.<n>We introduce a Magnitude-aware Cache (MagCache) that adaptively skips unimportant timesteps using an error modeling mechanism and adaptive caching strategy.<n> Experimental results show that MagCache achieves 2.1x and 2.68x speedups on Open-Sora and Wan 2.1, respectively.
  arXiv  Detail & Related papers  (2025-06-10T17:59:02Z)
• FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [46.57781555466333]
  Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks.<n>FastCache is a hidden-state-level caching and compression framework that accelerates DiT inference.<n> Empirical evaluations across multiple DiT variants demonstrate substantial reductions in latency and memory usage.
  arXiv  Detail & Related papers  (2025-05-26T05:58:49Z)
• dKV-Cache: The Cache for Diffusion Language Models [53.85291644298835]
  Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models.<n>We propose a KV-cache-like mechanism, delayed KV-Cache, for the denoising process of DLMs.<n>Our approach is motivated by the observation that different tokens have distinct representation dynamics throughout the diffusion process.
  arXiv  Detail & Related papers  (2025-05-21T17:32:10Z)
• EPIC: Efficient Position-Independent Context Caching for Serving Large Language Models [19.510078997414606]
  EPIC introduces position-independent context caching for large language models. EPIC delivers up to 8x improvements in TTFT and 7x throughput over existing systems.
  arXiv  Detail & Related papers  (2024-10-20T08:42:29Z)
• Efficient Inference of Vision Instruction-Following Models with Elastic Cache [76.44955111634545]
  We introduce Elastic Cache, a novel strategy for efficient deployment of instruction-following large vision-language models. We propose an importance-driven cache merging strategy to prune redundancy caches. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation.
  arXiv  Detail & Related papers  (2024-07-25T15:29:05Z)
• Hidden Web Caches Discovery [3.9272151228741716]
  This paper presents a novel methodology for cache detection using timing analysis. Our approach eliminates the dependency on cache status headers, making it applicable to any web server.
  arXiv  Detail & Related papers  (2024-07-23T08:58:06Z)
• CacheSquash: Making caches speculation-aware [11.499924192220274]
  Speculation is key to achieving high CPU performance, yet it enables risks like Spectre attacks.<n>We propose a novel mitigation, CacheSquash, that cancels mis-speculated memory accesses.<n>We implement CacheSquash on gem5 and show that it thwarts practical Spectre attacks, with near-zero performance overheads.
  arXiv  Detail & Related papers  (2024-06-17T21:43:39Z)
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching [56.286064975443026]
  We make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through a caching mechanism, can be readily removed even without updating the model parameters. We introduce a novel scheme, named Learningto-Cache (L2C), that learns to conduct caching in a dynamic manner for diffusion transformers. Experimental results show that L2C largely outperforms samplers such as DDIM and DPM-r, alongside prior cache-based methods at the same inference speed.
  arXiv  Detail & Related papers  (2024-06-03T18:49:57Z)
• MeanCache: User-Centric Semantic Caching for LLM Web Services [8.350378532274405]
  Caching is a natural solution to reduce inference costs on repeated queries.<n>This paper introduces MeanCache, a user-centric semantic cache for LLM-based services.<n>MeanCache identifies semantically similar queries to determine cache hit or miss.
  arXiv  Detail & Related papers  (2024-03-05T06:23:50Z)
• Efficient Prompt Caching via Embedding Similarity [26.456212783693545]
  We focus on the prediction accuracy of prompt caching for single-round question-answering tasks via embedding similarity. We propose a distillation-based method to fine-tune the existing embeddings for better better prediction. We also conduct simulations demonstrating that our trained models achieve better caching efficiency than the previous embedding model.
  arXiv  Detail & Related papers  (2024-02-02T06:34:11Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation [62.275143240798236]
  Video semantic segmentation dataset has limited categories per video. Less than 10% of queries could be matched to receive meaningful gradient updates during VSS training. Our method achieves state-of-the-art performance on the latest challenging VSS benchmark VSPW without bells and whistles.
  arXiv  Detail & Related papers  (2023-09-14T20:31:06Z)
• Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning [5.41530201129053]
  This paper proposes a novel memorization-based inference (MBI) that is compute free and only requires lookups. Specifically, our work capitalizes on the inference mechanism of the recurrent attention model (RAM) By leveraging the low-dimensionality of glimpse, our inference procedure stores key value pairs comprising of glimpse location, patch vector, etc. in a table. The computations are obviated during inference by utilizing the table to read out key-value pairs and performing compute-free inference by memorization.
  arXiv  Detail & Related papers  (2023-07-14T21:01:59Z)
• Clustered-patch Element Connection for Few-shot Learning [29.94768391960718]
  We propose a novel Clustered-patch Element Connection layer to correct the mismatch problem. Our CECNet outperforms the state-of-the-art methods on classification benchmark.
  arXiv  Detail & Related papers  (2023-04-20T05:22:27Z)
• Layer Ensembles [95.42181254494287]
  We introduce a method for uncertainty estimation that considers a set of independent categorical distributions for each layer of the network. We show that the method can be further improved by ranking samples, resulting in models that require less memory and time to run.
  arXiv  Detail & Related papers  (2022-10-10T17:52:47Z)
• Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching [72.50506500576746]
  We propose a novel caching paradigm, that we named approximate-key caching. While approximate cache hits alleviate DL inference workload and increase the system throughput, they however introduce an approximation error. We analytically model our caching system performance for classic LRU and ideal caches, we perform a trace-driven evaluation of the expected performance, and we compare the benefits of our proposed approach with the state-of-the-art similarity caching.
  arXiv  Detail & Related papers  (2021-12-13T13:49:11Z)
• SCNet: Training Inference Sample Consistency for Instance Segmentation [15.963615360741356]
  This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time. Experiments on the standard dataset reveal the effectiveness of the proposed method over multiple evaluation metrics, including box AP, mask AP, and inference speed.
  arXiv  Detail & Related papers  (2020-12-18T10:26:54Z)
• ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation [106.04777600352743]
  Differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. The single-path DARTS comes in, which only chooses a single-path submodel at each step. While being memory-friendly, it also comes with low computational costs. We propose a new algorithm called RObustifying Memory-Efficient NAS (ROME) to give a cure.
  arXiv  Detail & Related papers  (2020-11-23T06:34:07Z)
• Boosting Continuous Sign Language Recognition via Cross Modality Augmentation [135.30357113518127]
  Continuous sign language recognition deals with unaligned video-text pair. We propose a novel architecture with cross modality augmentation. The proposed framework can be easily extended to other existing CTC based continuous SLR architectures.
  arXiv  Detail & Related papers  (2020-10-11T15:07:50Z)
• Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations [33.50309671827902]
  We show how effective place recognition rates can be achieved on a new very large 10 million place dataset. We show how effective place recognition rates can be achieved on a new very large 10 million place dataset.
  arXiv  Detail & Related papers  (2020-01-23T10:31:28Z)

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.