{"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/opt-tree-speculative-decoding-with-adaptive","title":"OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure","arxiv_id":"2406.17276","date":"2024-06-25","proceeding":null,"authors":["Jikai Wang","Yi Su","Juntao Li","Qingrong Xia","Zi Ye","Xinyu Duan","Zhefeng Wang","Min Zhang"],"abstract":"Autoregressive language models demonstrate excellent performance in various scenarios. However, the inference efficiency is limited by its one-step-one-word generation mode, which has become a pressing problem recently as the models become increasingly larger. Speculative decoding employs a \"draft and then verify\" mechanism to allow multiple tokens to be generated in one step, realizing lossless acceleration. Existing methods mainly adopt fixed heuristic draft structures, which fail to adapt to different situations to maximize the acceptance length during verification. To alleviate this dilemma, we proposed OPT-Tree, an algorithm to construct adaptive and scalable draft trees. It searches the optimal tree structure that maximizes the mathematical expectation of the acceptance length in each decoding step. Experimental results reveal that OPT-Tree outperforms the existing draft structures and achieves a speed-up ratio of up to 3.2 compared with autoregressive decoding. If the draft model is powerful enough and the node budget is sufficient, it can generate more than ten tokens in a single step. Our code is available at https://github.com/Jikai0Wang/OPT-Tree.","url_abs":"https://arxiv.org/abs/2406.17276v3","url_pdf":"https://arxiv.org/pdf/2406.17276v3.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":"opt-tree-speculative-decoding-with-adaptive","repo_url":"https://github.com/jikai0wang/opt-tree","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.17276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17276"}},"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/jikai0wang/opt-tree","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"jikai0wang/opt-tree","repo_kind":"official","path":"opt_eagle/cnets.py","file_url":"https://github.com/jikai0wang/opt-tree/blob/HEAD/opt_eagle/cnets.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"f725bc2d76076485","entry":"apply_rotary_pos_emb","repo":"jikai0wang/opt-tree","repo_kind":"official","path":"opt_eagle/cnets.py","file_url":"https://github.com/jikai0wang/opt-tree/blob/HEAD/opt_eagle/cnets.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f725bc2d76076485"}},{"code_sha256_prefix":"f6e0c0fc3868b787","entry":"repeat_kv","repo":"jikai0wang/opt-tree","repo_kind":"official","path":"opt_classic/modeling_llama_kv.py","file_url":"https://github.com/jikai0wang/opt-tree/blob/HEAD/opt_classic/modeling_llama_kv.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6e0c0fc3868b787"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"jikai0wang/opt-tree","repo_kind":"official","path":"opt_eagle/cnets.py","file_url":"https://github.com/jikai0wang/opt-tree/blob/HEAD/opt_eagle/cnets.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"b71b0ed70aa2939c","entry":"rotate_half","repo":"jikai0wang/opt-tree","repo_kind":"official","path":"opt_classic/modeling_llama_kv.py","file_url":"https://github.com/jikai0wang/opt-tree/blob/HEAD/opt_classic/modeling_llama_kv.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b71b0ed70aa2939c"}},{"code_sha256_prefix":"bad260f6d71db00c","entry":"apply_rotary_pos_emb","repo":"jikai0wang/opt-tree","repo_kind":"official","path":"opt_classic/modeling_llama_kv.py","file_url":"https://github.com/jikai0wang/opt-tree/blob/HEAD/opt_classic/modeling_llama_kv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bad260f6d71db00c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}