{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124583"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124583","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"A large-scale model serving framework","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","abstract_has_math":false,"creators":["Zhou, Qinren"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Kindratenko, Volodymyr"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:02Z","subjects":["Hpc","Llm"],"languages":["en","eng"],"rights":["Copyright 2024 Qinren Zhou"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124583","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kindratenko, Volodymyr"]},{"key":"dc:creator","label":"Author","values":["Zhou, Qinren"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-04-30"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Hpc","Llm"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Qinren Zhou"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124583"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","The student, Qinren Zhou, accepted the attached license on 2024-04-26 at 07:11.","The student, Qinren Zhou, submitted this Thesis for approval on 2024-04-26 at 07:39.","This Thesis was approved for publication on 2024-04-30 at 08:59.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20652 on 2024-09-16 at 00:44:46","Recent advancements in large-scale models have significantly enhanced the capabilities of artificial intelligence. For instance, generative large language models (LLM) have broadly transformed our interactions with websites, devices, and information, in general. These models are increasingly valuable across various domains but pose substantial deployment challenges. They require intense computational resources because of their tens or hundreds of billions of model parameters, necessitating high-end GPUs with large memory capacities. High-performance computing (HPC) clusters, typically equipped with considerable GPU resources, are suitable for serving large-scale models. Nevertheless, their resources are finite and may become inadequate if user requests surpass the cluster’s capacity, unlike the scalable and nearly limitless resources of cloud services. Moreover, HPC clusters lack autoscaling capabilities, introducing additional challenges in accommodating dynamic user demands and optimizing resource utilization. This thesis presents a model-serving framework to optimize resource utilization and reduce model inference latency. By leveraging the Ray Serve library, the framework automatically manages the deployment and reclamation of models, thereby enabling efficient concurrent service to multiple users. The system incorporates a model-switching mechanism and a Slurm-compatible autoscaler. These features are specifically designed to address traditional HPC clusters’ finite resource and autoscaling limitations and significantly improve system responsiveness and user experience in AI applications."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A large-scale model serving framework"]}]}],"canonical_facts":{"dc:contributor":["Kindratenko, Volodymyr"],"dc:creator":["Zhou, Qinren"],"dc:date":["2024-05","2024-04-30"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","The student, Qinren Zhou, accepted the attached license on 2024-04-26 at 07:11.","The student, Qinren Zhou, submitted this Thesis for approval on 2024-04-26 at 07:39.","This Thesis was approved for publication on 2024-04-30 at 08:59.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20652 on 2024-09-16 at 00:44:46","Recent advancements in large-scale models have significantly enhanced the capabilities of artificial intelligence. For instance, generative large language models (LLM) have broadly transformed our interactions with websites, devices, and information, in general. These models are increasingly valuable across various domains but pose substantial deployment challenges. They require intense computational resources because of their tens or hundreds of billions of model parameters, necessitating high-end GPUs with large memory capacities. High-performance computing (HPC) clusters, typically equipped with considerable GPU resources, are suitable for serving large-scale models. Nevertheless, their resources are finite and may become inadequate if user requests surpass the cluster’s capacity, unlike the scalable and nearly limitless resources of cloud services. Moreover, HPC clusters lack autoscaling capabilities, introducing additional challenges in accommodating dynamic user demands and optimizing resource utilization. This thesis presents a model-serving framework to optimize resource utilization and reduce model inference latency. By leveraging the Ray Serve library, the framework automatically manages the deployment and reclamation of models, thereby enabling efficient concurrent service to multiple users. The system incorporates a model-switching mechanism and a Slurm-compatible autoscaler. These features are specifically designed to address traditional HPC clusters’ finite resource and autoscaling limitations and significantly improve system responsiveness and user experience in AI applications."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124583"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Qinren Zhou"],"dc:subject":["Hpc","Llm"],"dc:title":["A large-scale model serving framework"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:02Z"}