{"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/hygen-efficient-llm-serving-via-elastic","title":"HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location","arxiv_id":"2501.14808","date":"2025-01-15","proceeding":null,"authors":["Ting Sun","Penghan Wang","Fan Lai"],"abstract":"Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like document summarization. The existing deployment model, which dedicates machines to each workload, simplifies SLO management but often leads to poor resource utilization. This paper introduces HyGen, an interference-aware LLM serving system that enables efficient co-location of online and offline workloads while preserving latency requirements. HyGen incorporates two key innovations: (1) performance control mechanisms, including a latency predictor to estimate batch execution time and an SLO-aware profiler to quantify latency interference, and (2) SLO-aware offline scheduling policies that maximize serving throughput and prevent starvation, without compromising online serving latency. Our evaluation on production workloads shows that HyGen achieves up to 3.87x overall throughput and 5.84x offline throughput gains over online and hybrid serving baselines, respectively, while strictly satisfying latency SLOs.","url_abs":"https://arxiv.org/abs/2501.14808v3","url_pdf":"https://arxiv.org/pdf/2501.14808v3.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":"abstracts"},"code_links":[],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"management","task_name":"Management"},{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.14808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.14808"}},"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":"deterministic:regex_extraction","url":"https://github.com/UIUC-MLSys/HyGen","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7},"by_repo_kind":{"found_in_text":{"samples":7,"ran":7,"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":"68ee0f6ef8eb5004","entry":"convert_pyslice_to_tensor","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/model_executor/weight_utils.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/model_executor/weight_utils.py","link_basis":"harvester_set","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":"68ee0f6ef8eb5004"}},{"code_sha256_prefix":"75f9e29d6669a2b6","entry":"get_lock","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/model_executor/weight_utils.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/model_executor/weight_utils.py","link_basis":"harvester_set","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":"75f9e29d6669a2b6"}},{"code_sha256_prefix":"197a0f338024eca9","entry":"init_logger","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/logger.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/logger.py","link_basis":"harvester_set","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":"197a0f338024eca9"}},{"code_sha256_prefix":"43e0fdf0b69f6fd5","entry":"pad_to_alignment","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/model_executor/utils.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/model_executor/utils.py","link_basis":"harvester_set","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":"43e0fdf0b69f6fd5"}},{"code_sha256_prefix":"9dcee4f7df3d2300","entry":"pad_to_max","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/model_executor/utils.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/model_executor/utils.py","link_basis":"harvester_set","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":"9dcee4f7df3d2300"}},{"code_sha256_prefix":"04ad4cad55976bc7","entry":"prepare_hf_model_weights","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/model_executor/weight_utils.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/model_executor/weight_utils.py","link_basis":"harvester_set","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":"04ad4cad55976bc7"}},{"code_sha256_prefix":"2748c310c15773c2","entry":"round_up_to_multiple","repo":"UIUC-MLSys/HyGen","repo_kind":"found_in_text","path":"hygen/model_executor/utils.py","file_url":"https://github.com/UIUC-MLSys/HyGen/blob/HEAD/hygen/model_executor/utils.py","link_basis":"harvester_set","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":"2748c310c15773c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}