{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-5733"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-5733","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Implementation of a Local LLM Serving System for Agentic AI","abstract":"This thesis presents a system that allows large AI models to run directly on personal devices instead of relying on cloud servers. Recent advances in artificial intelligence, especially large language models (LLMs), have made it possible to build powerful applications such as chatbots, coding assistants, and intelligent agents. However, most of these systems run in the cloud, which raises concerns about privacy, latency, and cost. To address these issues, this work develops a local AI serving system that runs efficiently on a specialized hardware component called a Neural Processing Unit (NPU). The system provides a unified interface that supports multiple types of tasks, including text generation, image under- standing, speech recognition, and embedding-based search. It also supports advanced features such as streaming responses and tool calling, which are essential for building modern AI agents. The system is designed to be compatible with widely used APIs, allowing existing appli- cations to use it without modification. Experimental results show that the system works correctly across different tasks and improves efficiency through techniques such as prompt caching. Overall, this work demonstrates that it is possible to run advanced AI systems locally in a practical and efficient way, enabling faster, more private, and more flexible AI applications.","abstract_html":"This thesis presents a system that allows large AI models to run directly on personal devices instead of relying on cloud servers. Recent advances in artificial intelligence, especially large language models (LLMs), have made it possible to build powerful applications such as chatbots, coding assistants, and intelligent agents. However, most of these systems run in the cloud, which raises concerns about privacy, latency, and cost. To address these issues, this work develops a local AI serving system that runs efficiently on a specialized hardware component called a Neural Processing Unit (NPU). The system provides a unified interface that supports multiple types of tasks, including text generation, image under- standing, speech recognition, and embedding-based search. It also supports advanced features such as streaming responses and tool calling, which are essential for building modern AI agents. The system is designed to be compatible with widely used APIs, allowing existing appli- cations to use it without modification. Experimental results show that the system works correctly across different tasks and improves efficiency through techniques such as prompt caching. Overall, this work demonstrates that it is possible to run advanced AI systems locally in a practical and efficient way, enabling faster, more private, and more flexible AI applications.","abstract_has_math":false,"creators":["Ni, Zhiheng"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering (Holcomb Dept. of)","degree_department":null,"school":null,"contributors":["Tao Wei","Xiaoyong Yuan","Fatemeh Afghah"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:34:14Z","subjects":["Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/4796","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/4796","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-5733","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Tao Wei","Xiaoyong Yuan","Fatemeh Afghah"]},{"key":"dc:creator","label":"Author","values":["Ni, Zhiheng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-04-06T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-05-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering (Holcomb Dept. of)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/4796"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis presents a system that allows large AI models to run directly on personal devices instead of relying on cloud servers. Recent advances in artificial intelligence, especially large language models (LLMs), have made it possible to build powerful applications such as chatbots, coding assistants, and intelligent agents. However, most of these systems run in the cloud, which raises concerns about privacy, latency, and cost. To address these issues, this work develops a local AI serving system that runs efficiently on a specialized hardware component called a Neural Processing Unit (NPU). The system provides a unified interface that supports multiple types of tasks, including text generation, image under- standing, speech recognition, and embedding-based search. It also supports advanced features such as streaming responses and tool calling, which are essential for building modern AI agents. The system is designed to be compatible with widely used APIs, allowing existing appli- cations to use it without modification. Experimental results show that the system works correctly across different tasks and improves efficiency through techniques such as prompt caching. Overall, this work demonstrates that it is possible to run advanced AI systems locally in a practical and efficient way, enabling faster, more private, and more flexible AI applications."]},{"key":"dc:title","label":"Title","values":["Implementation of a Local LLM Serving System for Agentic AI"]}]}],"canonical_facts":{"dc:contributor":["Tao Wei","Xiaoyong Yuan","Fatemeh Afghah"],"dc:creator":["Ni, Zhiheng"],"dc:date.available":["2026-04-06T07:00:00Z"],"dc:date.created":["2026-05-01T07:00:00Z"],"dc:description.abstract":["This thesis presents a system that allows large AI models to run directly on personal devices instead of relying on cloud servers. Recent advances in artificial intelligence, especially large language models (LLMs), have made it possible to build powerful applications such as chatbots, coding assistants, and intelligent agents. However, most of these systems run in the cloud, which raises concerns about privacy, latency, and cost. To address these issues, this work develops a local AI serving system that runs efficiently on a specialized hardware component called a Neural Processing Unit (NPU). The system provides a unified interface that supports multiple types of tasks, including text generation, image under- standing, speech recognition, and embedding-based search. It also supports advanced features such as streaming responses and tool calling, which are essential for building modern AI agents. The system is designed to be compatible with widely used APIs, allowing existing appli- cations to use it without modification. Experimental results show that the system works correctly across different tasks and improves efficiency through techniques such as prompt caching. Overall, this work demonstrates that it is possible to run advanced AI systems locally in a practical and efficient way, enabling faster, more private, and more flexible AI applications."],"dc:identifier":["https://open.clemson.edu/all_theses/4796"],"dc:subject":["Electrical and Computer Engineering"],"dc:title":["Implementation of a Local LLM Serving System for Agentic AI"],"thesis:degree_discipline":["Electrical and Computer Engineering (Holcomb Dept. of)"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:34:14Z"}