{"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/slim-llm-salience-driven-mixed-precision","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","arxiv_id":"2405.14917","date":"2024-05-23","proceeding":null,"authors":["Wei Huang","Haotong Qin","Yangdong Liu","Yawei Li","Xianglong Liu","Luca Benini","Michele Magno","Xiaojuan Qi"],"abstract":"Large language models (LLMs) achieve remarkable performance in natural language understanding but require substantial computation and memory resources. Post-training quantization (PTQ) is a powerful compression technique extensively investigated in LLMs. However, existing PTQ methods are still not ideal in terms of accuracy and efficiency, especially with below 4 bit-widths. Standard PTQ methods using group-wise quantization suffer difficulties in quantizing LLMs accurately to such low-bit, but advanced methods remaining high-precision weights element-wisely are hard to realize their theoretical hardware efficiency. This paper presents a Salience-Driven Mixed-Precision Quantization scheme for LLMs, namely SliM-LLM. The scheme exploits the salience distribution of weights to determine optimal bit-width and quantizers for accurate LLM quantization, while aligning bit-width partition to groups for compact memory usage and fast integer inference. Specifically, the proposed SliM-LLM mainly relies on two novel techniques: (1) Salience-Determined Bit Allocation utilizes the clustering characteristics of salience distribution to allocate the bit-widths of each group, increasing the accuracy of quantized LLMs and maintaining the inference efficiency; (2) Salience-Weighted Quantizer Calibration optimizes the parameters of the quantizer by considering the element-wise salience within the group, balancing the maintenance of salient information and minimization of errors. Comprehensive experiments show that SliM-LLM significantly improves the accuracy of LLMs at ultra-low bits, e.g., 2-bit LLaMA-7B achieves a 5.5-times memory-saving than original model on NVIDIA A800 GPUs, and 48% decrease of perplexity compared to the state-of-the-art gradient-free PTQ method. Moreover, SliM-LLM+, which is integrated from the extension of SliM-LLM with gradient-based quantizers, further reduces perplexity by 35.1%.","url_abs":"https://arxiv.org/abs/2405.14917v1","url_pdf":"https://arxiv.org/pdf/2405.14917v1.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":"slim-llm-salience-driven-mixed-precision","repo_url":"https://github.com/Aaronhuang-778/SliM-LLM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.14917","atlas_url":"https://app.syntology.ai/?focus=2405.14917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14917"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.14917"},"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":"2405.14917"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.14917\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2405.14917"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.14917\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.14917"},"call":"get_concepts_for_paper(arxiv_id=\"2405.14917\")"}],"by_repo":[{"repo":"Aaronhuang-778/SliM-LLM","kind":"official","samples":13,"ran":8,"instrument":6,"unverified":5}],"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/2405.14917.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/2405.14917.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/Aaronhuang-778/SliM-LLM","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":6,"ran":1,"unverified":5},"n_samples":13,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"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":13,"ran":8,"n_ran_checked":2,"n_instrument":6,"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":13,"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":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","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":"c07dba9529e937b7","code_sha256_prefix":"c07dba9529e937b7","entry":"ampscaler_get_grad_norm","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parameters:list/1/Tensor, norm_type:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/ampscaler-get-grad-norm","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"c07dba9529e937b7"}},{"code_sha256":"87877d0c60858bff","code_sha256_prefix":"87877d0c60858bff","entry":"create_logger","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"output_dir:str/0/str, dist_rank:int/0/int, name:str/0/str","fixture_out_type":"Logger","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/create-logger","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"87877d0c60858bff"}},{"code_sha256":"a9e7f2cdf016b88b","code_sha256_prefix":"a9e7f2cdf016b88b","entry":"find_layers","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm/modelutils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm/modelutils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"module:callable/0/?, layers:list/1/callable, name:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/find-layers","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"a9e7f2cdf016b88b"}},{"code_sha256":"904cd61df2fe8fb9","code_sha256_prefix":"904cd61df2fe8fb9","entry":"find_layers","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/models/models_utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/models/models_utils.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/?, layers:list/1/callable, name:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/find-layers","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"904cd61df2fe8fb9"}},{"code_sha256":"4df9168e0a0c38eb","code_sha256_prefix":"4df9168e0a0c38eb","entry":"make_disjoint_window","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/models/models_utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/models/models_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pair:tuple/1/list","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/make-disjoint-window","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"4df9168e0a0c38eb"}},{"code_sha256":"aaa7723c864e0a5e","code_sha256_prefix":"aaa7723c864e0a5e","entry":"sort_layers_by_params","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/parallel_utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/parallel_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"layers:list/1/callable","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/sort-layers-by-params","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"aaa7723c864e0a5e"}},{"code_sha256":"94587954e392b665","code_sha256_prefix":"94587954e392b665","entry":"truncate_number","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/models/transformation.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/models/transformation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"number:Tensor/2/float, threshold:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"94587954e392b665"},"code_page":"/code/truncate-number","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"94587954e392b665"}},{"code_sha256":"4e53fbbdfa160f7d","code_sha256_prefix":"4e53fbbdfa160f7d","entry":"truncate_number","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/models/models_utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/models/models_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"number:Tensor/2/float, threshold:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4e53fbbdfa160f7d"},"code_page":"/code/truncate-number","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"4e53fbbdfa160f7d"}},{"code_sha256":"7e3ef1ed347af0f3","code_sha256_prefix":"7e3ef1ed347af0f3","entry":"assign_layers_to_gpus","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/parallel_utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/parallel_utils.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/assign-layers-to-gpus","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"7e3ef1ed347af0f3"}},{"code_sha256":"3c6439a3c61dd2bb","code_sha256_prefix":"3c6439a3c61dd2bb","entry":"get_lowest_occupied_gpu","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/parallel_utils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/parallel_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-lowest-occupied-gpu","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"3c6439a3c61dd2bb"}},{"code_sha256":"3b51341ed1a0b73e","code_sha256_prefix":"3b51341ed1a0b73e","entry":"get_pile","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/datautils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/datautils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-pile","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"3b51341ed1a0b73e"}},{"code_sha256":"bd4f416e271c2fb5","code_sha256_prefix":"bd4f416e271c2fb5","entry":"get_ptb","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/datautils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/datautils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-ptb","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"bd4f416e271c2fb5"}},{"code_sha256":"85420819f7a0df4a","code_sha256_prefix":"85420819f7a0df4a","entry":"get_wikitext2","repo":"Aaronhuang-778/SliM-LLM","repo_kind":"official","path":"slim-llm-plus/datautils.py","file_url":"https://github.com/Aaronhuang-778/SliM-LLM/blob/HEAD/slim-llm-plus/datautils.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-wikitext2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aaronhuang-778/SliM-LLM when it was checked","mcp_get_code":{"code_sha256":"85420819f7a0df4a"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"fc3c3249d774e40d957059839cfefbc79131c85a56ee2cca2567cea0cb8bec20","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}