相关论文: FOCUS: Boosting Schema-aware Access for KV Stores …

Graph-based multi-view clustering has achieved better performance than most non-graph approaches. However, in many real-world scenarios, the graph structure of data is not given or the quality of initial graph is poor. Additionally,…

Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by…

Transformers, while powerful, suffer from quadratic computational complexity and the ever-growing Key-Value (KV) cache of the attention mechanism. This paper introduces Trellis, a novel Transformer architecture with bounded memory that…

Disaggregated memory (DM) is a promising data center architecture that decouples CPU and memory into independent resource pools to improve resource utilization. Building on DM, memory-disaggregated key-value (KV) stores are adopted to…

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods…

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges,…

Cloud computing has attracted both end-users and Cloud Service Providers (CSPs) in recent years. Improving resource utilization rate (RUtR), such as CPU and memory usages on servers, while maintaining Quality-of-Service (QoS) is one key…

The increasing input sequence length in Large Language Models (LLMs) puts significant pressure on key-value (KV) cache storage, making efficient inference challenging. Explicitly distinguishing attention behavior into our self-defined…

Key-value (KV) cache compression has emerged as a critical technique for reducing the memory and latency overhead of autoregressive language models during inference. Prior approaches predominantly rely on query-key attention scores to rank…

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every…

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Dynamically scheduled high-level synthesis (HLS) enables the use of load-store queues (LSQs) which can disambiguate data hazards at circuit runtime, increasing throughput in codes with unpredictable memory accesses. However, the increased…

The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate over massive shared contexts. While Low-Rank Adaptation (LoRA) enables the efficient…

We propose novel attention architectures, Multi-matrix Factorization Attention (MFA) and MFA-Key-Reuse (MFA-KR). Existing variants for standard Multi-Head Attention (MHA), including SOTA methods like MLA, fail to maintain as strong…

Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cache quantization alleviates this cost, bit allocation between…

NoSQL databases are widely used in modern applications due to their scalability and schema flexibility, yet they often rely on eventual consistency models that limit reliable transaction processing. This study proposes a four-stage…

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…

The recent growth of web video sharing platforms has increased the demand for systems that can efficiently browse, retrieve and summarize video content. Query-aware multi-video summarization is a promising technique that caters to this…