{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FWTSF2R3RPH5CNDJLD5FAGIKCS","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":"c6c567b1a3fc336aa8b960d8a97de9ac03adda5775b5e8b22370453e6f25d5ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T16:10:41Z","title_canon_sha256":"61f30ebd3afbe30c25d7c97071b42dc648e38fc8f76f8b2f91f13bad00335bb5"},"schema_version":"1.0","source":{"id":"2408.11743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11743","created_at":"2026-07-05T08:57:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11743v1","created_at":"2026-07-05T08:57:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11743","created_at":"2026-07-05T08:57:48Z"},{"alias_kind":"pith_short_12","alias_value":"FWTSF2R3RPH5","created_at":"2026-07-05T08:57:48Z"},{"alias_kind":"pith_short_16","alias_value":"FWTSF2R3RPH5CNDJ","created_at":"2026-07-05T08:57:48Z"},{"alias_kind":"pith_short_8","alias_value":"FWTSF2R3","created_at":"2026-07-05T08:57:48Z"}],"graph_snapshots":[{"event_id":"sha256:97b374beb2e31e3401aaf7edeb8b6b3204456671835c6e6e79e40a978829433d","target":"graph","created_at":"2026-07-05T08:57:48Z","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/2408.11743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but has also been shown to yield substantial speedups for single-user inference, due to reduced memory movement, with low accuracy impact. Yet, it remains open whether speedups are achievable also in \\emph{batched} settings with multiple parallel clients, which are highly relevant for practical serving. It is unclear whether GPU kernels can be designed to remain","authors_text":"Dan Alistarh, Elias Frantar, Jiale Chen, Roberto L. Castro, Torsten Hoefler","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T16:10:41Z","title":"MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11743","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":"sha256:610ee47e02f0102b402842cdcaa21ccdba19411fa0e85435e92b6a78a84937cb","target":"record","created_at":"2026-07-05T08:57:48Z","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":"c6c567b1a3fc336aa8b960d8a97de9ac03adda5775b5e8b22370453e6f25d5ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T16:10:41Z","title_canon_sha256":"61f30ebd3afbe30c25d7c97071b42dc648e38fc8f76f8b2f91f13bad00335bb5"},"schema_version":"1.0","source":{"id":"2408.11743","kind":"arxiv","version":1}},"canonical_sha256":"2da722ea3b8bcfd1346958fa50190a14ab4e320c490443eb90b9e045cd567d07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2da722ea3b8bcfd1346958fa50190a14ab4e320c490443eb90b9e045cd567d07","first_computed_at":"2026-07-05T08:57:48.382696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:48.382696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b0Fc4CECzM5A6ZsELdolmpI6b8hA2hnDUgeRxpjNdqBYw8Mb2A4wIpz7JftHGRCOthNmnrwhh663HeEB1YjqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:48.383149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:610ee47e02f0102b402842cdcaa21ccdba19411fa0e85435e92b6a78a84937cb","sha256:97b374beb2e31e3401aaf7edeb8b6b3204456671835c6e6e79e40a978829433d"],"state_sha256":"47a1f6c2f591d259f8278c7a0924641a9226742be915f84232ebbcf816206a5c"}