{"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/adapmoe-adaptive-sensitivity-based-expert","title":"AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference","arxiv_id":"2408.10284","date":"2024-08-19","proceeding":null,"authors":["Shuzhang Zhong","Ling Liang","YuAn Wang","Runsheng Wang","Ru Huang","Meng Li"],"abstract":"Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges due to high on-demand loading overheads from managing sparsely activated experts. This paper introduces AdapMoE, an algorithm-system co-design framework for efficient MoE inference. AdapMoE features adaptive expert gating and management to reduce the on-demand loading overheads. We observe the heterogeneity of experts loading across layers and tokens, based on which we propose a sensitivity-based strategy to adjust the number of activated experts dynamically. Meanwhile, we also integrate advanced prefetching and cache management techniques to further reduce the loading latency. Through comprehensive evaluations on various platforms, we demonstrate AdapMoE consistently outperforms existing techniques, reducing the average number of activated experts by 25% and achieving a 1.35x speedup without accuracy degradation. Code is available at: https://github.com/PKU-SEC-Lab/AdapMoE.","url_abs":"https://arxiv.org/abs/2408.10284v1","url_pdf":"https://arxiv.org/pdf/2408.10284v1.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":"adapmoe-adaptive-sensitivity-based-expert","repo_url":"https://github.com/pku-sec-lab/adapmoe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"management","task_name":"Management"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.10284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10284"}},"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/pku-sec-lab/adapmoe","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"f01688d0434b6835","entry":"compute_metric","repo":"pku-sec-lab/adapmoe","repo_kind":"official","path":"benchmarks/chain-of-thought-hub/run_mmlu.py","file_url":"https://github.com/pku-sec-lab/adapmoe/blob/HEAD/benchmarks/chain-of-thought-hub/run_mmlu.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f01688d0434b6835"}},{"code_sha256_prefix":"cd763eaf1ac287e7","entry":"format_example","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"cd763eaf1ac287e7"}},{"code_sha256_prefix":"6ab745408cb8648b","entry":"format_subject","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6ab745408cb8648b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}