{"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/massive-language-models-can-be-accurately","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","arxiv_id":"2301.00774","date":"2023-01-02","proceeding":null,"authors":["Elias Frantar","Dan Alistarh"],"abstract":"We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models. We can execute SparseGPT on the largest available open-source models, OPT-175B and BLOOM-176B, in under 4.5 hours, and can reach 60% unstructured sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these models can be ignored at inference time. SparseGPT generalizes to semi-structured (2:4 and 4:8) patterns, and is compatible with weight quantization approaches. The code is available at: https://github.com/IST-DASLab/sparsegpt.","url_abs":"https://arxiv.org/abs/2301.00774v3","url_pdf":"https://arxiv.org/pdf/2301.00774v3.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":"massive-language-models-can-be-accurately","repo_url":"https://github.com/ist-daslab/sparsegpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"massive-language-models-can-be-accurately","repo_url":"https://github.com/baithebest/adagp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"massive-language-models-can-be-accurately","repo_url":"https://github.com/baithebest/sparsellm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"massive-language-models-can-be-accurately","repo_url":"https://github.com/eth-easl/deltazip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"massive-language-models-can-be-accurately","repo_url":"https://github.com/nvidia/tensorrt-model-optimizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"massive-language-models-can-be-accurately","repo_url":"https://github.com/nvlabs/maskllm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"OPT-175B","rank_in_archive_order":44,"of":54,"metrics":{"Accuracy":"43.94"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"SparseGPT (175B, 50% Sparsity)","rank_in_archive_order":46,"of":54,"metrics":{"Accuracy":"41.3"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"SparseGPT (175B, 4:8 Sparsity)","rank_in_archive_order":47,"of":54,"metrics":{"Accuracy":"39.85"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"SparseGPT (175B, 2:4 Sparsity)","rank_in_archive_order":48,"of":54,"metrics":{"Accuracy":"38.99"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"OPT-175B (50% Sparsity)","rank_in_archive_order":54,"of":54,"metrics":{"Accuracy":"25.6"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"OPT-175B","rank_in_archive_order":31,"of":47,"metrics":{"Accuracy":"71.04"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"SparseGPT 175B (50% sparsity)","rank_in_archive_order":36,"of":47,"metrics":{"Accuracy":"69.65"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"SparseGPT (175B, 4:8 Sparsity)","rank_in_archive_order":39,"of":47,"metrics":{"Accuracy":"68.35"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"SparseGPT 175B (2:4 sparsity)","rank_in_archive_order":41,"of":47,"metrics":{"Accuracy":"67.08"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"OPT 175B (50% Sparsity)","rank_in_archive_order":47,"of":47,"metrics":{"Accuracy":"28.03"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"SparseGPT (175B, 2:4 Sparsity)","rank_in_archive_order":13,"of":37,"metrics":{"Accuracy":"79.47"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"SparseGPT (175B, 4:8 Sparsity)","rank_in_archive_order":14,"of":37,"metrics":{"Accuracy":"78.77"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"SparseGPT (175B, 50% Sparsity)","rank_in_archive_order":17,"of":37,"metrics":{"Accuracy":"76.51"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"OPT-175B","rank_in_archive_order":19,"of":37,"metrics":{"Accuracy":"75.59"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"OPT-175B (50% Sparsity)","rank_in_archive_order":33,"of":37,"metrics":{"Accuracy":"0.02"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"SparseGPT (175B, 50% Sparsity)","rank_in_archive_order":1,"of":38,"metrics":{"Test perplexity":"8.21"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"OPT-175B","rank_in_archive_order":2,"of":38,"metrics":{"Test perplexity":"8.34"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"SparseGPT (175B, 4:8 Sparsity)","rank_in_archive_order":3,"of":38,"metrics":{"Test perplexity":"8.45"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"SparseGPT (175B, 2:4 Sparsity)","rank_in_archive_order":4,"of":38,"metrics":{"Test perplexity":"8.73"},"uses_additional_data":true},{"leaderboard":"/sota/language-modelling-on-wikitext-2","task":"Language Modelling","dataset":"WikiText-2","model":"OPT-175B (50% Sparsity)","rank_in_archive_order":38,"of":38,"metrics":{"Test perplexity":"234.77"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"OPT-175B","rank_in_archive_order":28,"of":67,"metrics":{"Accuracy":"81.07"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"SparseGPT 175B (50% Sparsity)","rank_in_archive_order":30,"of":67,"metrics":{"Accuracy":"80.63"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"SparseGPT 175B (4:8 Sparsity)","rank_in_archive_order":35,"of":67,"metrics":{"Accuracy":"79.54"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"SparseGPT 175B (2:4 Sparsity)","rank_in_archive_order":36,"of":67,"metrics":{"Accuracy":"79.54"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"OPT-175B (50% Sparsity)","rank_in_archive_order":66,"of":67,"metrics":{"Accuracy":"54.73"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-storycloze","task":"Question Answering","dataset":"StoryCloze","model":"OPT-175B","rank_in_archive_order":10,"of":23,"metrics":{"Accuracy":"79.82"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-storycloze","task":"Question Answering","dataset":"StoryCloze","model":"SparseGPT (175B, 50% Sparsity)","rank_in_archive_order":11,"of":23,"metrics":{"Accuracy":"78.87"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-storycloze","task":"Question Answering","dataset":"StoryCloze","model":"SparseGPT (175B, 4:8 Sparsity)","rank_in_archive_order":14,"of":23,"metrics":{"Accuracy":"77.02"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-storycloze","task":"Question Answering","dataset":"StoryCloze","model":"SparseGPT (175B, 2:4 Sparsity)","rank_in_archive_order":16,"of":23,"metrics":{"Accuracy":"76.19"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-storycloze","task":"Question Answering","dataset":"StoryCloze","model":"OPT-175B (50% Sparsity)","rank_in_archive_order":23,"of":23,"metrics":{"Accuracy":"47.10"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.00774","atlas_url":"https://app.syntology.ai/?focus=2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.00774"},"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":"2301.00774"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.00774\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2301.00774"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2301.00774\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2301.00774"},"call":"get_concepts_for_paper(arxiv_id=\"2301.00774\")"}],"by_repo":[{"repo":"ist-daslab/sparsegpt","kind":"official","samples":4,"ran":2,"instrument":2,"unverified":2,"placed_by_identical_code":1},{"repo":"baithebest/adagp","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.11695"],"harvested_for_calls":[{"arxiv_id":"2306.11695","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.11695"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.11695\")"}]},{"repo":"baithebest/sparsellm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.17946"],"harvested_for_calls":[{"arxiv_id":"2402.17946","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.17946"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.17946\")"}]},{"repo":"eth-easl/deltazip","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.05215"],"harvested_for_calls":[{"arxiv_id":"2312.05215","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.05215"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.05215\")"}]},{"repo":"nvidia/tensorrt-model-optimizer","kind":"listed","samples":8,"ran":7,"instrument":0,"unverified":1},{"repo":"nvlabs/maskllm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2409.17481"],"harvested_for_calls":[{"arxiv_id":"2409.17481","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.17481"},"call":"get_harvested_code_for_paper(arxiv_id=\"2409.17481\")"}]}],"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/2301.00774.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/2301.00774.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/baithebest/sparsellm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baithebest/adagp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eth-easl/deltazip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvlabs/maskllm","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ist-daslab/sparsegpt","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvidia/tensorrt-model-optimizer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":7,"unverified":3},"n_samples":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"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":4,"ran":2,"n_ran_checked":0,"n_instrument":2,"repositories":1},"listed":{"samples":8,"ran":7,"n_ran_checked":7,"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":9,"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":8,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","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":"cd666c16d4aaa66d","code_sha256_prefix":"cd666c16d4aaa66d","entry":"get_bloom","repo":"ist-daslab/sparsegpt","repo_kind":"official","path":"bloom.py","file_url":"https://github.com/ist-daslab/sparsegpt/blob/HEAD/bloom.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:str/0/str","fixture_out_type":"MockBloomForCausalLM","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-bloom","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cd666c16d4aaa66d"}},{"code_sha256":"f1c26f01bf2f39a9","code_sha256_prefix":"f1c26f01bf2f39a9","entry":"get_language_model_from_vl","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/export/model_utils.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/export/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, strict:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"f1c26f01bf2f39a9"}},{"code_sha256":"bc6cfb190b953479","code_sha256_prefix":"bc6cfb190b953479","entry":"get_model_type","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/export/model_utils.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/export/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"str","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":"/code/get-model-type","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"bc6cfb190b953479"}},{"code_sha256":"887f43fe08a6472d","code_sha256_prefix":"887f43fe08a6472d","entry":"get_opt","repo":null,"repo_kind":"official","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"model:str/0/str","fixture_out_type":"MockOPTForCausalLM","code_page":"/code/get-opt","census":null,"placed_by_identical_code":{"repo":"ist-daslab/sparsegpt","path":"opt.py","file_url":"https://github.com/IST-DASLab/sparsegpt/blob/HEAD/opt.py","papers":["2025.findings-emnlp.1054"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"887f43fe08a6472d"}},{"code_sha256":"140c6ce5087cbbce","code_sha256_prefix":"140c6ce5087cbbce","entry":"is_multimodal_model","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/export/model_utils.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/export/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"bool","level_recorded_at":"2026-09-25T08:34:48.807261+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"140c6ce5087cbbce"}},{"code_sha256":"f36d24bde785f7cc","code_sha256_prefix":"f36d24bde785f7cc","entry":"pad_weights","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/export/trtllm/model_config_utils.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/export/trtllm/model_config_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"weights:Tensor/2/float, tp_size:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f36d24bde785f7cc"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"f36d24bde785f7cc"}},{"code_sha256":"e9eca650c1a383f2","code_sha256_prefix":"e9eca650c1a383f2","entry":"prepare_enc_dec_export_dir","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/export/trtllm/tensorrt_llm_utils.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/export/trtllm/tensorrt_llm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tensorrt_llm_config:dict/0/?, export_root:PosixPath/0/?","fixture_out_type":"PosixPath","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"e9eca650c1a383f2"}},{"code_sha256":"e3133ddfe52e03a0","code_sha256_prefix":"e3133ddfe52e03a0","entry":"student_input_bypass_fwd_hook","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/distill/layerwise_distillation_model.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/distill/layerwise_distillation_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"module:callable/0/?, input:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"e3133ddfe52e03a0"}},{"code_sha256":"54d01cbd62cf758a","code_sha256_prefix":"54d01cbd62cf758a","entry":"svd","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/quantization/model_calib.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/quantization/model_calib.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"weight:Tensor/2/float, rank:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","retrieve_with":{"tool":"get_code","code_sha256":"54d01cbd62cf758a"},"code_page":"/code/svd","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"54d01cbd62cf758a"}},{"code_sha256":"5076786563dd8499","code_sha256_prefix":"5076786563dd8499","entry":"bloom_sequential","repo":"ist-daslab/sparsegpt","repo_kind":"official","path":"bloom.py","file_url":"https://github.com/ist-daslab/sparsegpt/blob/HEAD/bloom.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/bloom-sequential","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5076786563dd8499"}},{"code_sha256":"bf403ae47e912dc1","code_sha256_prefix":"bf403ae47e912dc1","entry":"opt_sequential","repo":"ist-daslab/sparsegpt","repo_kind":"official","path":"opt.py","file_url":"https://github.com/ist-daslab/sparsegpt/blob/HEAD/opt.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/opt-sequential","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bf403ae47e912dc1"}},{"code_sha256":"1c19ab0c6ad9a45c","code_sha256_prefix":"1c19ab0c6ad9a45c","entry":"postprocess_amax","repo":"nvidia/tensorrt-model-optimizer","repo_kind":"listed","path":"modelopt/torch/quantization/model_quant.py","file_url":"https://github.com/nvidia/tensorrt-model-optimizer/blob/HEAD/modelopt/torch/quantization/model_quant.py","link_basis":"harvester_set","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":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","mcp_get_code":{"code_sha256":"1c19ab0c6ad9a45c"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b429ba9836583e8b407b505aaab7fca3d5713ee2f66a8ba52e7d0c2c291dc31c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}