Related papers: Enhancing Instruction Prefetching via Cache and TL…

Recently, edge caching and multicasting arise as two promising technologies to support high-data-rate and low-latency delivery in wireless communication networks. In this paper, we design three transmission schemes aiming to minimize the…

Accelerators, like GPUs, have become a trend to deliver future performance desire, and sharing the same virtual memory space between CPUs and GPUs is increasingly adopted to simplify programming. However, address translation, which is the…

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Training LLMs larger than the aggregated memory of multiple GPUs is increasingly necessary due to the faster growth of LLM sizes compared to GPU memory. To this end, multi-tier host memory or disk offloading techniques are proposed by state…

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill…

As capacity and complexity of on-chip cache memory hierarchy increases, the service cost to the critical loads from Last Level Cache (LLC), which are frequently repeated, has become a major concern. The processor may stall for a…

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

Each LLM serving request goes through two phases. The first is prefill which processes the entire input prompt and produces the first output token and the second is decode which generates the rest of output tokens, one-at-a-time. Prefill…

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion…

Large Language Models (LLMs) like ChatGPT and Llama have revolutionized natural language processing and search engine dynamics. However, these models incur exceptionally high computational costs. For instance, GPT-3 consists of 175 billion…

Automated bug priority inference can reduce the time overhead of bug triagers for priority assignments, improving the efficiency of software maintenance. Currently, there are two orthogonal lines for this task, i.e., traditional machine…

Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical…

A new form of caching, namely application-level caching, has been recently employed in web applications to improve their performance and increase scalability. It consists of the insertion of caching logic into the application base code to…

Despite the advancements of open-source large language models (LLMs), e.g., LLaMA, they remain significantly limited in tool-use capabilities, i.e., using external tools (APIs) to fulfill human instructions. The reason is that current…

Large Language Models (LLMs) are primarily designed for batch processing. Existing methods for adapting LLMs to streaming rely either on expensive re-encoding or specialized architectures with limited scalability. This work identifies three…

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Last-Level Cache (LLC) represents the bulk of a modern CPU processor's transistor budget and is essential for application performance as LLC enables fast access to data in contrast to much slower main memory. However, applications with…

Test-Time Scaling (TTS) is an important method for improving the performance of Large Language Models (LLMs) by using additional computation during the inference phase. However, current studies do not systematically analyze how policy…