{"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":"/code/quantizelinear","entry":"QuantizeLinear","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":5},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.17471","paper":"/paper/arxiv-2605-17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"facebookresearch/WinQ","path":"utils/reinitialize_callback.py","file_url":"https://github.com/facebookresearch/WinQ/blob/HEAD/utils/reinitialize_callback.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"03e772bc280be950","mcp_get_code":{"code_sha256":"03e772bc280be950"}},{"arxiv_id":"2503.02394","paper":"/paper/bhvit-binarized-hybrid-vision-transformer","title":"BHViT: Binarized Hybrid Vision Transformer","date":"2025-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IMRL/BHViT","path":"transformer/BHViT.py","file_url":"https://github.com/IMRL/BHViT/blob/HEAD/transformer/BHViT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cefbcad32882f70","mcp_get_code":{"code_sha256":"0cefbcad32882f70"}},{"arxiv_id":"2502.02631","paper":"/paper/paretoq-scaling-laws-in-extremely-low-bit-llm","title":"ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization","date":"2025-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/LLM-QAT","path":"models/utils_quant.py","file_url":"https://github.com/facebookresearch/LLM-QAT/blob/HEAD/models/utils_quant.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c6cc2e44490f66e2","mcp_get_code":{"code_sha256":"c6cc2e44490f66e2"}},{"arxiv_id":"2402.14905","paper":"/paper/mobilellm-optimizing-sub-billion-parameter","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/LLM-QAT","path":"models/modeling_llama_quant.py","file_url":"https://github.com/facebookresearch/LLM-QAT/blob/HEAD/models/modeling_llama_quant.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3013c6ea70f1983f","mcp_get_code":{"code_sha256":"3013c6ea70f1983f"}},{"arxiv_id":"2203.11239","paper":"/paper/dq-bart-efficient-sequence-to-sequence-model","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","date":"2022-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-research/dq-bart","path":"quant/modeling_bart_quant.py","file_url":"https://github.com/amazon-research/dq-bart/blob/HEAD/quant/modeling_bart_quant.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"07ed61cb853ea6a3","mcp_get_code":{"code_sha256":"07ed61cb853ea6a3"}}]}