{"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/multi-candidate-speculative-decoding","title":"Multi-Candidate Speculative Decoding","arxiv_id":"2401.06706","date":"2024-01-12","proceeding":null,"authors":["Sen yang","ShuJian Huang","Xinyu Dai","Jiajun Chen"],"abstract":"Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a sequence of tokens) from a fast draft model that is then verified in parallel by the target model. However, the acceptance rate of candidate tokens receives limitations from several factors, such as the model, the dataset, and the decoding setup. This paper proposes sampling multiple candidates from a draft model and then organising them in batches for verification. We design algorithms for efficient multi-candidate verification while maintaining the distribution of the target model. Our approach shows significant improvements in acceptance rates on multiple datasets and models, consistently outperforming standard speculative decoding.","url_abs":"https://arxiv.org/abs/2401.06706v1","url_pdf":"https://arxiv.org/pdf/2401.06706v1.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":"multi-candidate-speculative-decoding","repo_url":"https://github.com/njunlp/mcsd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.06706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06706"}},"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/njunlp/mcsd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran":2,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/model/llama_tree_attn/modeling_llama.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"f725bc2d76076485","entry":"apply_rotary_pos_emb","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/model/llama_tree_attn/modeling_llama.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f725bc2d76076485"}},{"code_sha256_prefix":"507f475feb734647","entry":"compute_intermediate_size","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"507f475feb734647"}},{"code_sha256_prefix":"1d1e62539117448a","entry":"get_tree_attn_self_mask","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/inference/strategies.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/inference/strategies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d1e62539117448a"}},{"code_sha256_prefix":"c5bcf01d18bba63d","entry":"read_json","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/model/llama_tree_attn/modeling_llama.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"731285361b7dea0e","entry":"write_model","repo":"njunlp/mcsd","repo_kind":"official","path":"MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"731285361b7dea0e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}