{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/optimize-weight-rounding-via-signed-gradient","title":"Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs","arxiv_id":"2309.05516","date":"2023-09-11","proceeding":null,"authors":["Wenhua Cheng","Weiwei Zhang","Haihao Shen","Yiyang Cai","Xin He","Kaokao Lv","Yi Liu"],"abstract":"Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements. Weight-only quantization has emerged as a promising solution, significantly reducing memory and storage needs without sacrificing too much performance. In this study, we introduce SignRound, a method that leverages signed gradient descent (SignSGD) to optimize rounding values and weight clipping in just 200 steps. SignRound integrates the advantages of Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ), delivering exceptional results across 2 to 4 bits while minimizing tuning costs and avoiding additional inference overhead. For example, SignRound achieved absolute average accuracy improvements ranging from 6.91% to 33.22% at 2bits, as measured by the average zero-shot accuracy across 11 tasks. It also demonstrates strong generalization in recent models, achieving near-lossless 4-bit quantization in most scenarios. The source code is publicly available at https://github.com/intel/auto-round.","url_abs":"https://arxiv.org/abs/2309.05516v5","url_pdf":"https://arxiv.org/pdf/2309.05516v5.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":"optimize-weight-rounding-via-signed-gradient","repo_url":"https://github.com/intel/auto-round","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"optimize-weight-rounding-via-signed-gradient","repo_url":"https://github.com/intel/neural-compressor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"optimize-weight-rounding-via-signed-gradient","repo_url":"https://github.com/rasmith/vllm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"optimize-weight-rounding-via-signed-gradient","repo_url":"https://github.com/vllm-project/vllm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.05516","atlas_url":"https://app.syntology.ai/?focus=2309.05516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05516"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.05516"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.05516"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.05516\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2309.05516"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.05516\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.05516"},"call":"get_concepts_for_paper(arxiv_id=\"2309.05516\")"}],"by_repo":[{"repo":"intel/auto-round","kind":"official","samples":10,"ran":5,"instrument":0,"unverified":5},{"repo":"intel/neural-compressor","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.10944"],"harvested_for_calls":[{"arxiv_id":"2310.10944","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.10944"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.10944\")"}]},{"repo":"rasmith/vllm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2309.06180"],"harvested_for_calls":[{"arxiv_id":"2309.06180","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.06180"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.06180\")"}]},{"repo":"vllm-project/vllm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2608.19920"],"harvested_for_calls":[{"arxiv_id":"2608.19920","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2608.19920"},"call":"get_harvested_code_for_paper(arxiv_id=\"2608.19920\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2309.05516.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2309.05516.svg"},"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/vllm-project/vllm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel/auto-round","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel/neural-compressor","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rasmith/vllm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":5},"n_samples":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":10,"ran":5,"n_ran_checked":5,"n_instrument":0,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"e52a1adf6e14e3f0","code_sha256_prefix":"e52a1adf6e14e3f0","entry":"apply_chat_template_to_samples","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/calib_dataset.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/calib_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"samples:list/1/str, tokenizer:callable/0/?, seqlen:int/0/int, system_prompt:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e52a1adf6e14e3f0"}},{"code_sha256":"7dde89a31f2370e3","code_sha256_prefix":"7dde89a31f2370e3","entry":"get_code_calibration_dataset","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/calib_dataset.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/calib_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"nsamples:int/0/int, datasets_version:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7dde89a31f2370e3"}},{"code_sha256":"3bfdd2b43d1ae35d","code_sha256_prefix":"3bfdd2b43d1ae35d","entry":"is_block_quantizer_config","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/algorithms/config_resolver.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/algorithms/config_resolver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"config:dict/0/?","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3bfdd2b43d1ae35d"}},{"code_sha256":"7cd246188fdf9359","code_sha256_prefix":"7cd246188fdf9359","entry":"prepare_special_model_block_inputs","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/special_model_handler.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/special_model_handler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"block:callable/0/?, rotary_input:Tensor/3/float, input_others:dict/0/?, positional_inputs:NoneType/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7cd246188fdf9359"}},{"code_sha256":"34b4d7cc1934723b","code_sha256_prefix":"34b4d7cc1934723b","entry":"register_dataset","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/calib_dataset.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/calib_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"name:str/0/str","fixture_out_type":"function","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/register-dataset","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"34b4d7cc1934723b"}},{"code_sha256":"8dc37cb8349ffb98","code_sha256_prefix":"8dc37cb8349ffb98","entry":"get_algorithm_class","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/algorithms/config_resolver.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/algorithms/config_resolver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-algorithm-class","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8dc37cb8349ffb98"}},{"code_sha256":"9c9808ac09eabbca","code_sha256_prefix":"9c9808ac09eabbca","entry":"get_algorithm_entry","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/algorithms/registry.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/algorithms/registry.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9c9808ac09eabbca"}},{"code_sha256":"2286f55df29e9f20","code_sha256_prefix":"2286f55df29e9f20","entry":"is_preprocessor_config","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/algorithms/config_resolver.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/algorithms/config_resolver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2286f55df29e9f20"}},{"code_sha256":"b0f8a04cc8cf723a","code_sha256_prefix":"b0f8a04cc8cf723a","entry":"resolve_algorithm_alias","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/algorithms/registry.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/algorithms/registry.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b0f8a04cc8cf723a"}},{"code_sha256":"c8689d617f69a13e","code_sha256_prefix":"c8689d617f69a13e","entry":"resolve_algorithm_names","repo":"intel/auto-round","repo_kind":"official","path":"auto_round/algorithms/registry.py","file_url":"https://github.com/intel/auto-round/blob/HEAD/auto_round/algorithms/registry.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c8689d617f69a13e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e2de8b0f2855936c489eef5774c81d0db7c673d166c894e161c87d48ee682523","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}