Related papers: CacheClip: Accelerating RAG with Effective KV Cach…
The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…
Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required…
Key-value (KV) caching has emerged as a crucial optimization technique for accelerating inference in large language models (LLMs). By allowing the attention operation to scale linearly rather than quadratically with the total sequence…
Multi-agent large language model (LLM) systems are increasingly adopted for complex language processing tasks that require communication and coordination among agents. However, these systems often suffer substantial overhead from repeated…
While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we…
Large language models (LLMs) are increasingly applied in long-context scenarios such as multi-turn conversations. However, long contexts pose significant challenges for inference efficiency, including high memory overhead from Key-Value…
Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…
Large Language Models(LLMs) have had a profound impact on AI applications, particularly in the domains of long-text comprehension and generation. KV Cache technology is one of the most widely used techniques in the industry. It ensures…
Fine-tuning is an immensely resource-intensive process when retraining Large Language Models (LLMs) to incorporate a larger body of knowledge. Although many fine-tuning techniques have been developed to reduce the time and computational…
Retrieval-Augmented Generation (RAG) improves model output accuracy by leveraging external knowledge bases, serving as an effective solution to address hallucination issues and knowledge-update delays in Large Language Models (LLMs).…
Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…
Multi-agent LLM systems routinely generate multiple candidate responses that are aggregated by an LLM judge. To reduce the dominant prefill cost in such pipelines, recent work advocates KV cache reuse across partially shared contexts and…
Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive…
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation Download PDF Neal Gregory Lawton, Alfy Samuel, Anoop Kumar, Daben Liu Published: 20 Aug 2025, Retrieval augmented generation (RAG) is a popular…
KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…
Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall…
Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-score-based KV cache pruning shows promise, it faces critical practical limitations: attention scores…
Retrieval-augmented generation (RAG) has been extensively used as a de facto paradigm in various large language model (LLM)-driven applications on mobile devices, such as mobile assistants leveraging personal emails or meeting records.…
Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing their capabilities with advanced reasoning. However, deploying these models in production environments presents a significant QoS challenge: the…
Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can…