{"id":"https://openalex.org/W4417516982","doi":"https://doi.org/10.48550/arxiv.2505.07531","title":"QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads","display_name":"QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4417516982","doi":"https://doi.org/10.48550/arxiv.2505.07531"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.07531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07531","pdf_url":"https://arxiv.org/pdf/2505.07531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.07531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060934705","display_name":"Muhammad Aurangzeb Ahmad","orcid":"https://orcid.org/0000-0001-7449-5956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad, Muhammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033584789","display_name":"Khurram Usman Mazher","orcid":"https://orcid.org/0000-0001-8760-391X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mazher, Khurram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072405628","display_name":"Shimaa Akram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akram, Saqib","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039300325","display_name":"Abdul Tameem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tameem, Ahmad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071566785","display_name":"Saad Bin Nasir","orcid":"https://orcid.org/0000-0003-1488-0021"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nasir, Saad Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.33559998869895935,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.33559998869895935,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.21150000393390656,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.08540000021457672,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.8151999711990356},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6765999794006348},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6287999749183655},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45739999413490295},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4154999852180481},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.359499990940094}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8151999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368999719619751},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6765999794006348},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39730000495910645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C2777894999","wikidata":"https://www.wikidata.org/wiki/Q4781758","display_name":"Approx","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.07531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07531","pdf_url":"https://arxiv.org/pdf/2505.07531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.07531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.07531","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.07531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07531","pdf_url":"https://arxiv.org/pdf/2505.07531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417516982.pdf","grobid_xml":"https://content.openalex.org/works/W4417516982.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,85],"present":[1],"QuantX:":[2],"a":[3],"tailored":[4],"suite":[5],"of":[6,16,63,104,128],"recipes":[7,129],"for":[8,67,73],"LLM":[9,121],"and":[10,51,78,98,130],"VLM":[11],"quantization.":[12],"It":[13],"is":[14],"capable":[15],"quantizing":[17],"down":[18,70],"to":[19,37,71,107],"3-bit":[20],"resolutions":[21],"with":[22],"minimal":[23],"loss":[24],"in":[25,30,102,135],"performance.":[26],"The":[27],"quantization":[28,83,110,122],"strategies":[29],"QuantX":[31,58,92],"take":[32],"into":[33,93,119],"account":[34],"hardware-specific":[35],"constraints":[36],"achieve":[38],"efficient":[39],"dequantization":[40],"during":[41],"inference":[42],"ensuring":[43],"flexible":[44],"trade-off":[45],"between":[46],"runtime":[47,105],"speed,":[48],"memory":[49],"requirement":[50],"model":[52,66],"accuracy.":[53],"Our":[54],"results":[55],"demonstrate":[56],"that":[57,124,132],"achieves":[59],"performance":[60],"within":[61],"6%":[62],"the":[64,94,108,120,126],"unquantized":[65],"LlaVa-v1.6":[68],"quantized":[69],"3-bits":[72],"multiple":[74],"end":[75],"user":[76],"tasks":[77],"outperforms":[79],"recently":[80],"published":[81],"state-of-the-art":[82],"techniques.":[84],"further":[86],"integrate":[87],"one":[88],"particular":[89],"technique":[90],"from":[91,112],"popular":[95],"Llama.cpp":[96],"framework":[97],"show":[99],"its":[100],"feasibility":[101],"terms":[103],"compared":[106],"mainstream":[109],"techniques":[111],"Llama.cpp.":[113],"Lastly,":[114],"this":[115],"manuscript":[116],"provides":[117],"insights":[118],"process":[123],"motivated":[125],"range":[127],"options":[131],"are":[133],"incorporated":[134],"QuantX.":[136]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}