{"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/alpaserve-statistical-multiplexing-with-model","title":"AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving","arxiv_id":"2302.11665","date":"2023-02-22","proceeding":null,"authors":["Zhuohan Li","Lianmin Zheng","Yinmin Zhong","Vincent Liu","Ying Sheng","Xin Jin","Yanping Huang","Zhifeng Chen","Hao Zhang","Joseph E. Gonzalez","Ion Stoica"],"abstract":"Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single device. In this paper, we demonstrate that model parallelism can be additionally used for the statistical multiplexing of multiple devices when serving multiple models, even when a single model can fit into a single device. Our work reveals a fundamental trade-off between the overhead introduced by model parallelism and the opportunity to exploit statistical multiplexing to reduce serving latency in the presence of bursty workloads. We explore the new trade-off space and present a novel serving system, AlpaServe, that determines an efficient strategy for placing and parallelizing collections of large deep learning models across a distributed cluster. Evaluation results on production workloads show that AlpaServe can process requests at up to 10x higher rates or 6x more burstiness while staying within latency constraints for more than 99% of requests.","url_abs":"https://arxiv.org/abs/2302.11665v2","url_pdf":"https://arxiv.org/pdf/2302.11665v2.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":[{"paper_slug":"alpaserve-statistical-multiplexing-with-model","repo_url":"https://github.com/alpa-projects/mms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"alpaserve-statistical-multiplexing-with-model","repo_url":"https://github.com/alpa-projects/alpa","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.11665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11665"}},"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/alpa-projects/mms","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alpa-projects/alpa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"2ad6f0eafb1d0278","entry":"bound","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/mesh_profiling.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/mesh_profiling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ad6f0eafb1d0278"}},{"code_sha256_prefix":"6b8c79e585dcba90","entry":"device_id_to_str","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/device_mesh.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/device_mesh.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b8c79e585dcba90"}},{"code_sha256_prefix":"81967bfdd1ac49b2","entry":"get_execution_timer_name","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/mesh_executable.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/mesh_executable.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81967bfdd1ac49b2"}},{"code_sha256_prefix":"64ca3a2333822fea","entry":"get_num_devices_for_whole_batch","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/data_loader.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64ca3a2333822fea"}},{"code_sha256_prefix":"d1e29ce48e4b4248","entry":"get_sync_func_worker","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/mesh_executable.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/mesh_executable.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1e29ce48e4b4248"}},{"code_sha256_prefix":"c08c15bcbdf1ca55","entry":"next_array_uuids","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/device_mesh.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/device_mesh.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c08c15bcbdf1ca55"}},{"code_sha256_prefix":"dd568196508417cd","entry":"slice_jaxpr_with_mesh_assignment","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/create_state_parallel.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/create_state_parallel.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd568196508417cd"}},{"code_sha256_prefix":"bd00be190ebf0c0e","entry":"to_np_dtype","repo":"alpa-projects/alpa","repo_kind":"official","path":"alpa/mesh_profiling.py","file_url":"https://github.com/alpa-projects/alpa/blob/HEAD/alpa/mesh_profiling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd00be190ebf0c0e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}