Related papers: SAIL: SRAM-Accelerated LLM Inference System with L…

To improve the efficiency of distributed large language model (LLM) inference, various parallelization strategies, such as tensor and pipeline parallelism, have been proposed. However, the distinct computational characteristics inherent in…

SRAM-based Analog Compute-in-Memory (ACiM) demonstrates promising energy efficiency for deep neural network (DNN) processing. Nevertheless, efforts to optimize efficiency frequently compromise accuracy, and this trade-off remains…

How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In…

Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory…

Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems…

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Large Language Model (LLM) inference is rapidly becoming a core datacenter service, yet current serving stacks keep the host CPU on the critical path for orchestration and token-level control. This makes LLM performance sensitive to CPU…

Text generation is a compelling sub-field of natural language processing, aiming to generate human-readable text from input words. In particular, the decoder-only generative models, such as generative pre-trained transformer (GPT), are…

Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and…

Offline Imitation Learning (IL) methods such as Behavior Cloning are effective at acquiring complex robotic manipulation skills. However, existing IL-trained policies are confined to executing the task at the same speed as shown in…

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…

As large language models (LLMs) grow in size and deployment scale, quantization has become an essential technique for reducing memory footprint and improving inference efficiency. However, existing quantization toolkits often lack…

Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that…

To overcome the well-known memory bottleneck of AI chips, 3D stacked architectures that employ advanced packaging technology with high-density through-silicon vias (TSVs) pins have proven to be a promising solution. The 3D-stacked AI chip…

Modern LLM serving now spans multi-stage pipelines including RAG retrieval and KV cache reuse, each with distinct compute, memory, and latency demands. Inference engines expose a large configuration space with no systematic navigation…

The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill over to CPU memory; however, traditional…

In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…