{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3TAVVLNRE5LC6LLWEXNUPCQEYA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7018be39f46538673e1bcf890a6f2dd7103b5929eb0e368f618427cb016eba11","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-10-16T02:16:53Z","title_canon_sha256":"8c2908500b429f7e99908bf81e42a40afedb76fd25ad45eb795414e69aae7410"},"schema_version":"1.0","source":{"id":"2410.12168","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12168","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12168v1","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12168","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"3TAVVLNRE5LC","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"3TAVVLNRE5LC6LLW","created_at":"2026-07-05T09:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"3TAVVLNR","created_at":"2026-07-05T09:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:050df91389779d099df9c86d137778d37c2de8f5eac95e877a94e10daa861923","target":"graph","created_at":"2026-07-05T09:21:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.12168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or 4-bit weight-only quantization, achieve limited performance improvements due to poor support for low-precision (e.g., 4-bit) activation. This work, for the first time, realizes practical W4A4KV4 serving for LLMs, fully utilizing the INT4 tensor cores on modern GPUs and reducing the memory bottleneck caused by the KV cache. Specifically, we propose a novel fin","authors_text":"Haimeng Ren, Lian Liu, Long Cheng, Mengdi Wang, Xiaowei Li, Ying Wang, Yinhe Han, Yudong Pan, Zhaohui Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-10-16T02:16:53Z","title":"COMET: Towards Partical W4A4KV4 LLMs Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12168","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d7673ecf1f5e155b5f60c0e9e5c4048a6786c4ba89475c520e6f8768d4a97137","target":"record","created_at":"2026-07-05T09:21:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7018be39f46538673e1bcf890a6f2dd7103b5929eb0e368f618427cb016eba11","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-10-16T02:16:53Z","title_canon_sha256":"8c2908500b429f7e99908bf81e42a40afedb76fd25ad45eb795414e69aae7410"},"schema_version":"1.0","source":{"id":"2410.12168","kind":"arxiv","version":1}},"canonical_sha256":"dcc15aadb127562f2d7625db478a04c02e4cd0688d73b6de55663e17e52523af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcc15aadb127562f2d7625db478a04c02e4cd0688d73b6de55663e17e52523af","first_computed_at":"2026-07-05T09:21:15.167410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:15.167410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6BwFxUec3RnXKrbbsEynylHE8MzFFnwp4UA/lcHQ1OT1w4873J2uiT/i7Hu4LAvhfeB60XszYubeVH3A9AMKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:15.167793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12168","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7673ecf1f5e155b5f60c0e9e5c4048a6786c4ba89475c520e6f8768d4a97137","sha256:050df91389779d099df9c86d137778d37c2de8f5eac95e877a94e10daa861923"],"state_sha256":"df9e55c400371f3b5d567064d8e135d41aeb5fa1ed85da8e687697321269d5c0"}