Related papers: Towards Resiliency in Large Language Model Serving…
Emergency communication systems face disruptions due to packet loss, bandwidth constraints, poor signal quality, delays, and jitter in VoIP systems, leading to degraded real-time service quality. Victims in distress often struggle to convey…
Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…
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…
Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique…
Cloud computing has become inevitable for every digital service which has exponentially increased its usage. However, a tremendous surge in cloud resource demand stave off service availability resulting into outages, performance…
While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…
As Large Language Models (LLMs) become ubiquitous, the challenge of securing them against adversarial "jailbreaking" attacks has intensified. Current defense strategies often rely on computationally expensive external classifiers or brittle…
Serving numerous users and requests concurrently requires good fairness in Large Language Models (LLMs) serving system. This ensures that, at the same cost, the system can meet the Service Level Objectives (SLOs) of more users , such as…
Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…
We present the design, implementation and engineering experience in building and deploying MegaScale, a production system for training large language models (LLMs) at the scale of more than 10,000 GPUs. Training LLMs at this scale brings…
Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…
Heterogeneous device-edge-cloud computing infrastructures have become widely adopted in telecommunication operators and Wide Area Networks (WANs), offering multi-tier computational support for emerging intelligent services. With the rapid…
Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…
We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Prompt tokens determine initial KV usage, and each…
Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…
In the context of Machine Learning as a Service (MLaaS) clouds, the extensive use of Large Language Models (LLMs) often requires efficient management of significant query loads. When providing real-time inference services, several…
Generative AI like the Large Language Models (LLMs) has become more available for the general consumer in recent years. Publicly available services, e.g., ChatGPT, perform token generation on networked cloud server hardware, effectively…
Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…
In machine learning (ML), the inference phase is the process of applying pre-trained models to new, unseen data with the objective of making predictions. During the inference phase, end-users interact with ML services to gain insights,…
Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…