Related papers: C2CServe: Leveraging NVLink-C2C for Elastic Server…

The extensive use of GPUs in cloud computing and the growing need for multitenancy have driven the development of innovative solutions for efficient GPU resource management. Multi-Instance GPU (MIG) technology from NVIDIA enables shared GPU…

GPUs exploit a high degree of thread-level parallelism to hide long-latency stalls. Due to the heterogeneous compute requirements of different applications, there is a growing need to share the GPU across multiple applications in…

The rapid increase in LLM model sizes and the growing demand for long-context inference have made memory a critical bottleneck in GPU-accelerated serving systems. Although high-bandwidth memory (HBM) on GPUs offers fast access, its limited…

Since current widely available network protocols/systems are mainly throughput-oriented designs, meeting stringent delay requirements of new applications such as virtual reality and vehicle-to-vehicle communications on cellular network…

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE)…

Large language model (LLM) serving is now limited by the key-value (KV) cache. During decode, each new token rereads prior KV state, so attention becomes a bandwidth- and capacity-heavy memory task. HBM-PIM helps by moving attention closer…

Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile memory (NVM) promises major efficiency improvements in deep neural…

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…

In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving…

When multiple processor cores (CPUs) and a GPU integrated together on the same chip share the off-chip DRAM, requests from the GPU can heavily interfere with requests from the CPUs, leading to low system performance and starvation of cores.…

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…

Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads…

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the…

Large Language Models (LLMs) have resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput has emerged as a key metric that…

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 foundation-model ecosystem remains highly centralized because training requires immense compute resources and is therefore largely limited to large cloud operators. Edge-assisted foundation model training that harnesses spare compute on…

In modern server CPUs, the Last-Level Cache (LLC) serves not only as a victim cache for higher-level private caches but also as a buffer for low-latency DMA transfers between CPU cores and I/O devices through Direct Cache Access (DCA).…

Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models (LLMs). However, the execution characteristics of MoE inference are changing rapidly and increasingly mismatch the assumptions underlying existing…

The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounced in multi-tenant environments, where shared resources must…

Shared virtual memory (SVM) is key in heterogeneous systems on chip (SoCs), which combine a general-purpose host processor with a many-core accelerator, both for programmability and to avoid data duplication. However, SVM can bring a…