{"id":"https://openalex.org/keywords/large-language-model-serving","display_name":"large language model serving","description":"The systems and techniques for delivering large language model inference to users or applications, including scheduling, batching, and resource management.","display_name_alternatives":["serving large language models","large language model inference serving","LLM inference serving","LLM serving"],"ids":{"openalex":"https://openalex.org/keywords/large-language-model-serving","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.2872,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.2872,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.1687,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":549,"cited_by_count":8916,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/large-language-model-serving","updated_date":"2026-11-16T04:05:30","created_date":"2026-09-30T00:00:00"}
