{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNIKXE2PMVMVJFU2KSXDVONDCD","short_pith_number":"pith:FNIKXE2P","schema_version":"1.0","canonical_sha256":"2b50ab934f655954969a54ae3ab9a310cc6da34d21fcdf884b5ab600c9ae2a38","source":{"kind":"arxiv","id":"2412.17560","version":4},"attestation_state":"computed","paper":{"title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Zeng, Fangmin Chen, Lean Fu, Shu Yang, Songwei Liu, Xing Mei","submitted_at":"2024-12-23T13:28:15Z","abstract_excerpt":"Model compression has emerged as a mainstream solution to reduce memory usage and computational overhead. This paper presents Group Quantization and Sparse Acceleration (GQSA), a novel compression technique tailored for LLMs. Traditional methods typically focus exclusively on either quantization or sparsification, but relying on a single strategy often results in significant performance loss at high compression rates. In contrast, GQSA integrates quantization and sparsification in a tightly coupled manner, leveraging GPU-friendly structured group sparsity and quantization for efficient acceler"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.17560","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T13:28:15Z","cross_cats_sorted":[],"title_canon_sha256":"117225284ea0b8405df07d2f16de42fcb0fe41ffe9749942021ebd8c0044f16f","abstract_canon_sha256":"b5369134005290f1e1761bfe8b39732518f7c887861cb906563b99873ecf83bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:59.988058Z","signature_b64":"9NbpSEVmap7Q7jPmNIsRD7f1c42DEN8oc6E0CBz+ciB57QrHikeeiRmq7hkps3m4OzQj/UswuFScBOdxz3NZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b50ab934f655954969a54ae3ab9a310cc6da34d21fcdf884b5ab600c9ae2a38","last_reissued_at":"2026-07-05T11:43:59.987570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:59.987570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Zeng, Fangmin Chen, Lean Fu, Shu Yang, Songwei Liu, Xing Mei","submitted_at":"2024-12-23T13:28:15Z","abstract_excerpt":"Model compression has emerged as a mainstream solution to reduce memory usage and computational overhead. This paper presents Group Quantization and Sparse Acceleration (GQSA), a novel compression technique tailored for LLMs. Traditional methods typically focus exclusively on either quantization or sparsification, but relying on a single strategy often results in significant performance loss at high compression rates. In contrast, GQSA integrates quantization and sparsification in a tightly coupled manner, leveraging GPU-friendly structured group sparsity and quantization for efficient acceler"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17560","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.17560/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.17560","created_at":"2026-07-05T11:43:59.987621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17560v4","created_at":"2026-07-05T11:43:59.987621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17560","created_at":"2026-07-05T11:43:59.987621+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNIKXE2PMVMV","created_at":"2026-07-05T11:43:59.987621+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNIKXE2PMVMVJFU2","created_at":"2026-07-05T11:43:59.987621+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNIKXE2P","created_at":"2026-07-05T11:43:59.987621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.22575","citing_title":"S2O: Early Stopping for Sparse Attention via Online Permutation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD","json":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD.json","graph_json":"https://pith.science/api/pith-number/FNIKXE2PMVMVJFU2KSXDVONDCD/graph.json","events_json":"https://pith.science/api/pith-number/FNIKXE2PMVMVJFU2KSXDVONDCD/events.json","paper":"https://pith.science/paper/FNIKXE2P"},"agent_actions":{"view_html":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD","download_json":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD.json","view_paper":"https://pith.science/paper/FNIKXE2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17560&json=true","fetch_graph":"https://pith.science/api/pith-number/FNIKXE2PMVMVJFU2KSXDVONDCD/graph.json","fetch_events":"https://pith.science/api/pith-number/FNIKXE2PMVMVJFU2KSXDVONDCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD/action/storage_attestation","attest_author":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD/action/author_attestation","sign_citation":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD/action/citation_signature","submit_replication":"https://pith.science/pith/FNIKXE2PMVMVJFU2KSXDVONDCD/action/replication_record"}},"created_at":"2026-07-05T11:43:59.987621+00:00","updated_at":"2026-07-05T11:43:59.987621+00:00"}