Related papers: Mooncake: A KVCache-centric Disaggregated Architec…

LLM inference must meet strict latency SLOs (e.g., 100 ms P99 time-between-tokens) while maximizing goodput. Yet, real-world variability in prompt and response lengths skews compute-intensive prefill and memory-bound decode phases, making…

The increased memory demands of workloads is putting high pressure on Last Level Caches (LLCs). Unfortunately, there is limited opportunity to increase the capacity of LLCs due to the area and power requirements of the underlying SRAM…

Large language models (LLMs) enable long-context tasks but face efficiency challenges due to the growing key-value (KV) cache. We propose LeanK, a learning-based method that prunes unimportant key (K) cache channels by leveraging static…

The limited HBM capacity has become the primary bottleneck for hosting an increasing number of larger-scale GPU tasks. While demand paging extends capacity via host DRAM, it incurs up to 78x slowdown due to the massive working sets and poor…

Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC) is promising but hindered by a fundamental granularity mismatch. LLMs operate on fragmented token sequences, whereas entities are the fundamental units in…

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due to the quadratic computational complexity of attention in…

In this paper, we present a novel cache design based on Multi-Level Cell Spin-Transfer Torque RAM (MLC STTRAM) that can dynamically adapt the set capacity and associativity to use efficiently the full potential of MLC STTRAM. We exploit the…

The use of Large Language Models (LLMs) for querying relational data has given rise to relQuery, a workload pattern that applies templated LLM calls to structured tables. As relQuery services become more widely adopted in applications such…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, where different…

We introduce Mi:dm 2.0, a bilingual large language model (LLM) specifically engineered to advance Korea-centric AI. This model goes beyond Korean text processing by integrating the values, reasoning patterns, and commonsense knowledge…

Multimodal large language models (MLLMs) extend the capabilities of large language models (LLMs) by combining heterogeneous model architectures to handle diverse modalities like images and audio. However, this inherent heterogeneity in MLLM…

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model…

Long-running agentic tasks, such as deep research, require multi-hop reasoning over information distributed across multiple webpages and documents. In such tasks, the LLM context is dominated by tokens from external retrieval, causing…

Use-case-specific network slicing in decentralized multi-tenancy cloud environments is a promising approach to bridge the gap between the demand and supply of resources in next-generation communication networks. Our findings associate…

Interactive intelligent computing applications are increasingly prevalent, creating a need for AI/ML platforms optimized to reduce per-event latency while maintaining high throughput and efficient resource management. Yet many intelligent…

Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to…

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…

Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization…