{"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/clover-2-accurate-inference-for-regressive","title":"Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding","arxiv_id":"2408.00264","date":"2024-08-01","proceeding":null,"authors":[],"abstract":"Large Language Models (LLMs) frequently suffer from inefficiencies, largely attributable to the discord between the requirements of auto-regressive decoding and the architecture of contemporary GPUs. Recently, regressive lightweight speculative decoding has garnered attention for its notable efficiency improvements in text generation tasks. This approach utilizes a lightweight regressive draft model, like a Recurrent Neural Network (RNN) or a single transformer decoder layer, leveraging sequential information to iteratively predict potential tokens. Specifically, RNN draft models are computationally economical but tend to deliver lower accuracy, while attention decoder layer models exhibit the opposite traits. This paper presents Clover-2, an advanced iteration of Clover, an RNN-based draft model designed to achieve comparable accuracy to that of attention decoder layer models while maintaining minimal computational overhead. Clover-2 enhances the model architecture and incorporates knowledge distillation to increase Clover's accuracy and improve overall efficiency. We conducted experiments using the open-source Vicuna 7B and LLaMA3-Instruct 8B models. The results demonstrate that Clover-2 surpasses existing methods across various model architectures, showcasing its efficacy and robustness.","url_abs":"https://arxiv.org/abs/2408.00264v1","url_pdf":"https://arxiv.org/pdf/2408.00264v1.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":"clover-2-accurate-inference-for-regressive","repo_url":"https://github.com/XiaoBin1992/clover","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.00264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00264"}},"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/XiaoBin1992/clover","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":5,"ran":5,"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"listed":{"samples":17,"ran":13,"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":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/modeling_eagle.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/modeling_eagle.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":"3c76e52815c5401d","entry":"repeat_kv","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/clover2.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/clover2.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":"3c76e52815c5401d"}},{"code_sha256_prefix":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/modeling_mixtral_kv.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/modeling_mixtral_kv.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":"d61c483a3c2b3156"}},{"code_sha256_prefix":"f725bc2d76076485","entry":"apply_rotary_pos_emb","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/modeling_eagle.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/modeling_eagle.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":"9a65a30d006fc96e","entry":"apply_rotary_pos_emb","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/clover2.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/clover2.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":"9a65a30d006fc96e"}},{"code_sha256_prefix":"8a738587f4d897b9","entry":"generate_tree_buffers","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/utils_alpha.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils_alpha.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":"8a738587f4d897b9"}},{"code_sha256_prefix":"aadc9c83d7ec2701","entry":"initialize_past_key_values","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/kv_cache.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/kv_cache.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aadc9c83d7ec2701"}},{"code_sha256_prefix":"a40c43d3dbc369d3","entry":"pad_path","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/utils.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils.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":"a40c43d3dbc369d3"}},{"code_sha256_prefix":"f02fecb5f780c3f8","entry":"prepare_logits_processor","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/utils_alpha.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils_alpha.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":"f02fecb5f780c3f8"}},{"code_sha256_prefix":"f6e0c0fc3868b787","entry":"repeat_kv","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/modeling_llama_kv.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6e0c0fc3868b787"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/modeling_eagle.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/modeling_eagle.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":"e03d53ba9d4f9ae5","entry":"rotate_half","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/clover2.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/clover2.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":"e03d53ba9d4f9ae5"}},{"code_sha256_prefix":"b71b0ed70aa2939c","entry":"rotate_half","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/modeling_llama_kv.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b71b0ed70aa2939c"}},{"code_sha256_prefix":"bad260f6d71db00c","entry":"apply_rotary_pos_emb","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/modeling_llama_kv.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bad260f6d71db00c"}},{"code_sha256_prefix":"d9308d9bf18cd072","entry":"load_balancing_loss_func","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/modeling_mixtral_kv.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/modeling_mixtral_kv.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":"d9308d9bf18cd072"}},{"code_sha256_prefix":"fdb811155913ebca","entry":"prepare_logits_processor","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/utils.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils.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":"fdb811155913ebca"}},{"code_sha256_prefix":"b54951ffbd7a4fc0","entry":"timer","repo":"XiaoBin1992/clover","repo_kind":"listed","path":"clover/model/utils.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils.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":"b54951ffbd7a4fc0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}