{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/llumnix-dynamic-scheduling-for-large-language","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","arxiv_id":"2406.03243","date":"2024-06-05","proceeding":null,"authors":["Biao Sun","Ziming Huang","Hanyu Zhao","Wencong Xiao","Xinyi Zhang","Yong Li","Wei Lin"],"abstract":"Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.","url_abs":"https://arxiv.org/abs/2406.03243v1","url_pdf":"https://arxiv.org/pdf/2406.03243v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"llumnix-dynamic-scheduling-for-large-language","repo_url":"https://github.com/alibabapai/llumnix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.03243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03243"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibabapai/llumnix","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a1410ef4c8fb44be","entry":"from_llumnix_args_config","repo":"alibabapai/llumnix","repo_kind":"official","path":"llumnix/arg_utils.py","file_url":"https://github.com/alibabapai/llumnix/blob/HEAD/llumnix/arg_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a1410ef4c8fb44be"}},{"code_sha256_prefix":"659e41417067eb12","entry":"get_llumnix_actor_name","repo":"alibabapai/llumnix","repo_kind":"official","path":"llumnix/ray_utils.py","file_url":"https://github.com/alibabapai/llumnix/blob/HEAD/llumnix/ray_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"659e41417067eb12"}},{"code_sha256_prefix":"7fd81d5894bd8f5d","entry":"get_placement_group_name","repo":"alibabapai/llumnix","repo_kind":"official","path":"llumnix/ray_utils.py","file_url":"https://github.com/alibabapai/llumnix/blob/HEAD/llumnix/ray_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7fd81d5894bd8f5d"}},{"code_sha256_prefix":"74428262a55426ae","entry":"get_placement_group_unit_id","repo":"alibabapai/llumnix","repo_kind":"official","path":"llumnix/ray_utils.py","file_url":"https://github.com/alibabapai/llumnix/blob/HEAD/llumnix/ray_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74428262a55426ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}