{"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/generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","arxiv_id":"2402.11809","date":"2024-02-19","proceeding":null,"authors":["Hanling Yi","Feng Lin","Hongbin Li","Peiyang Ning","Xiaotian Yu","Rong Xiao"],"abstract":"This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \\textbf{S}mart \\textbf{P}arallel \\textbf{A}uto-\\textbf{C}orrect d\\textbf{E}coding (SPACE), an innovative approach designed for achieving lossless acceleration of LLMs. By integrating semi-autoregressive inference and speculative decoding capabilities, SPACE uniquely enables autoregressive LLMs to parallelize token generation and verification. This is realized through a specialized semi-autoregressive supervised fine-tuning process that equips existing LLMs with the ability to simultaneously predict multiple tokens. Additionally, an auto-correct decoding algorithm facilitates the simultaneous generation and verification of token sequences within a single model invocation. Through extensive experiments on a range of LLMs, SPACE has demonstrated inference speedup ranging from 2.7x-4.0x on HumanEval-X while maintaining output quality.","url_abs":"https://arxiv.org/abs/2402.11809v3","url_pdf":"https://arxiv.org/pdf/2402.11809v3.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":"generation-meets-verification-accelerating","repo_url":"https://github.com/cteant/space","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"generation-meets-verification-accelerating","repo_url":"https://github.com/hiyouga/llama-factory","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"humaneval","task_name":"HumanEval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11809"}},"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/cteant/space","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hiyouga/llama-factory","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":3,"ran_honours":1,"ran":2,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"cteant/space","repo_kind":"official","path":"src/models/modeling_llama.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"5cfeaee89a75c5ff","entry":"apply_rotary_pos_emb","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_chatglm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_chatglm.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":"5cfeaee89a75c5ff"}},{"code_sha256_prefix":"d9db9f86b30f9ac0","entry":"dequantize_cache_torch","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_qwen.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_qwen.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9db9f86b30f9ac0"}},{"code_sha256_prefix":"546c22d62993a619","entry":"dropout_add","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_falcon.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_falcon.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":"1fec7a76f0d171a6","entry":"quantize_cache_v","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_qwen.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_qwen.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fec7a76f0d171a6"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_internlm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_internlm.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":"cteant/space","repo_kind":"official","path":"src/models/modeling_falcon.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_falcon.py","link_basis":"first_harvest_node","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":"d7e378ee7899fbde","entry":"split_tensor_along_last_dim","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_chatglm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_chatglm.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7e378ee7899fbde"}},{"code_sha256_prefix":"b42659b1a3b456f9","entry":"apply_rotary_pos_emb","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_internlm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_internlm.py","link_basis":"first_harvest_node","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":"b42659b1a3b456f9"}},{"code_sha256_prefix":"b4acc4f0962c97ca","entry":"build_alibi_tensor","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_falcon.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_falcon.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"}},{"code_sha256_prefix":"237019e36b9481d9","entry":"default_init","repo":"cteant/space","repo_kind":"official","path":"src/models/modeling_chatglm.py","file_url":"https://github.com/cteant/space/blob/HEAD/src/models/modeling_chatglm.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":"237019e36b9481d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}