{"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/bita-bi-directional-tuning-for-lossless","title":"BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models","arxiv_id":"2401.12522","date":"2024-01-23","proceeding":null,"authors":["Feng Lin","Hanling Yi","Hongbin Li","Yifan Yang","Xiaotian Yu","Guangming Lu","Rong Xiao"],"abstract":"Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional Tuning for lossless Acceleration (BiTA), an innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification. Inspired by the concept of prompt tuning, we enhance LLMs with a parameter-efficient design called bi-directional tuning for the capability in semi-autoregressive generation. Employing efficient tree-based decoding, the models perform draft candidate generation and verification in parallel, ensuring outputs identical to their autoregressive counterparts under greedy sampling. BiTA serves as a lightweight plug-in module, seamlessly boosting the inference efficiency of existing LLMs without requiring additional assistance models or incurring significant extra memory costs. Applying the proposed BiTA, LLaMA-2-70B-Chat achieves a 2.7$\\times$ speedup on the MT-Bench benchmark. Extensive experiments confirm our method surpasses state-of-the-art acceleration techniques.","url_abs":"https://arxiv.org/abs/2401.12522v2","url_pdf":"https://arxiv.org/pdf/2401.12522v2.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":"bita-bi-directional-tuning-for-lossless","repo_url":"https://github.com/linfeng93/bita","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.12522","atlas_url":"https://app.syntology.ai/?focus=2401.12522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12522"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/linfeng93/bita","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":0,"samples":[{"code_sha256_prefix":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"linfeng93/bita","repo_kind":"official","path":"src/modeling_llama_if.py","file_url":"https://github.com/linfeng93/bita/blob/HEAD/src/modeling_llama_if.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"f725bc2d76076485","entry":"apply_rotary_pos_emb","repo":"linfeng93/bita","repo_kind":"official","path":"src/modeling_llama_if.py","file_url":"https://github.com/linfeng93/bita/blob/HEAD/src/modeling_llama_if.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f725bc2d76076485"}},{"code_sha256_prefix":"546c22d62993a619","entry":"dropout_add","repo":"linfeng93/bita","repo_kind":"official","path":"src/modeling_falcon_if.py","file_url":"https://github.com/linfeng93/bita/blob/HEAD/src/modeling_falcon_if.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":"546c22d62993a619"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"linfeng93/bita","repo_kind":"official","path":"src/modeling_llama_if.py","file_url":"https://github.com/linfeng93/bita/blob/HEAD/src/modeling_llama_if.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"c89eed9eaa3332c2","entry":"rotate_half","repo":"linfeng93/bita","repo_kind":"official","path":"src/modeling_falcon_if.py","file_url":"https://github.com/linfeng93/bita/blob/HEAD/src/modeling_falcon_if.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":"c89eed9eaa3332c2"}},{"code_sha256_prefix":"b4acc4f0962c97ca","entry":"build_alibi_tensor","repo":"linfeng93/bita","repo_kind":"official","path":"src/modeling_falcon_if.py","file_url":"https://github.com/linfeng93/bita/blob/HEAD/src/modeling_falcon_if.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":"b4acc4f0962c97ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}