{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ICEHJ57YFE2UVC36KQXLWBTVSY","short_pith_number":"pith:ICEHJ57Y","canonical_record":{"source":{"id":"2411.15715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-11-24T04:53:10Z","cross_cats_sorted":[],"title_canon_sha256":"33d2dd8d064275276de07060e8dc0376b4af2d44b7bb24dd0f22b374792512a4","abstract_canon_sha256":"5fe60d6341eadf557de6724abc5f3f247c5946bd932a1cdbdb2b40ad514362bf"},"schema_version":"1.0"},"canonical_sha256":"408874f7f829354a8b7e542ebb0675962a51334974566ba62ea1c50ad0b5525e","source":{"kind":"arxiv","id":"2411.15715","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15715","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15715v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15715","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"ICEHJ57YFE2U","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"ICEHJ57YFE2UVC36","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"ICEHJ57Y","created_at":"2026-07-05T09:39:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ICEHJ57YFE2UVC36KQXLWBTVSY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-11-24T04:53:10Z","cross_cats_sorted":[],"title_canon_sha256":"33d2dd8d064275276de07060e8dc0376b4af2d44b7bb24dd0f22b374792512a4","abstract_canon_sha256":"5fe60d6341eadf557de6724abc5f3f247c5946bd932a1cdbdb2b40ad514362bf"},"schema_version":"1.0"},"canonical_sha256":"408874f7f829354a8b7e542ebb0675962a51334974566ba62ea1c50ad0b5525e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:39.854565Z","signature_b64":"JD5jBLxTp5HahXrIu9w5OBSLf/McmJ6OFFXd7Gsc88rEg1LSVt4Ra6X6a3p9BuNB04xej0wuxeaTCtgQ3V3iDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"408874f7f829354a8b7e542ebb0675962a51334974566ba62ea1c50ad0b5525e","last_reissued_at":"2026-07-05T09:39:39.853990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:39.853990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15715","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BywG7mEi0jmQ6oAvRDIURxTr3Va7d68TDup7z+4/g1nASeaoSaon+ny0HVBuzLXuYOFrqYuTqGJMwA01sMBkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:30:20.993944Z"},"content_sha256":"04a3b80e33073de0b785ccd38a328cb93f328cd5d391539362860b009af9404d","schema_version":"1.0","event_id":"sha256:04a3b80e33073de0b785ccd38a328cb93f328cd5d391539362860b009af9404d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ICEHJ57YFE2UVC36KQXLWBTVSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Scheduling for Efficient Inference of Large Language Models on Single Moderate GPU Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Shaohuai Shi, Wenxiang Lin, Xiaowen Chu, Xinglin Pan, Xuan Wang","submitted_at":"2024-11-24T04:53:10Z","abstract_excerpt":"Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can shrink model sizes but often impair accuracy, making them unsuitable for practical applications. In this work, we introduce \\modelname{}, a high-performance inference engine designed to speed up LLM inference without compromising model accuracy. \\modelname{} incorporates three innovative methods to increase inference efficiency: 1) model partitioning to allow "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15715","kind":"arxiv","version":1},"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/2411.15715/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+F9pStX3PJ0aToVbujHS7z/qAhieoXzRlDQNsHLoCwUVdvhZ+WgOB9l19EZZTmp2nwoPLtk5zypKsTTnxdXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:30:20.994824Z"},"content_sha256":"1f28468070d405babd90b16ab39fa3f1562f8b12a7c77e1a88d5163346fdbcd9","schema_version":"1.0","event_id":"sha256:1f28468070d405babd90b16ab39fa3f1562f8b12a7c77e1a88d5163346fdbcd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICEHJ57YFE2UVC36KQXLWBTVSY/bundle.json","state_url":"https://pith.science/pith/ICEHJ57YFE2UVC36KQXLWBTVSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICEHJ57YFE2UVC36KQXLWBTVSY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T19:30:20Z","links":{"resolver":"https://pith.science/pith/ICEHJ57YFE2UVC36KQXLWBTVSY","bundle":"https://pith.science/pith/ICEHJ57YFE2UVC36KQXLWBTVSY/bundle.json","state":"https://pith.science/pith/ICEHJ57YFE2UVC36KQXLWBTVSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICEHJ57YFE2UVC36KQXLWBTVSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ICEHJ57YFE2UVC36KQXLWBTVSY","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":"5fe60d6341eadf557de6724abc5f3f247c5946bd932a1cdbdb2b40ad514362bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-11-24T04:53:10Z","title_canon_sha256":"33d2dd8d064275276de07060e8dc0376b4af2d44b7bb24dd0f22b374792512a4"},"schema_version":"1.0","source":{"id":"2411.15715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15715","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15715v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15715","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"ICEHJ57YFE2U","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"ICEHJ57YFE2UVC36","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"ICEHJ57Y","created_at":"2026-07-05T09:39:39Z"}],"graph_snapshots":[{"event_id":"sha256:1f28468070d405babd90b16ab39fa3f1562f8b12a7c77e1a88d5163346fdbcd9","target":"graph","created_at":"2026-07-05T09:39:39Z","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/2411.15715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can shrink model sizes but often impair accuracy, making them unsuitable for practical applications. In this work, we introduce \\modelname{}, a high-performance inference engine designed to speed up LLM inference without compromising model accuracy. \\modelname{} incorporates three innovative methods to increase inference efficiency: 1) model partitioning to allow ","authors_text":"Shaohuai Shi, Wenxiang Lin, Xiaowen Chu, Xinglin Pan, Xuan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-11-24T04:53:10Z","title":"Task Scheduling for Efficient Inference of Large Language Models on Single Moderate GPU Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15715","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":"sha256:04a3b80e33073de0b785ccd38a328cb93f328cd5d391539362860b009af9404d","target":"record","created_at":"2026-07-05T09:39:39Z","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":"5fe60d6341eadf557de6724abc5f3f247c5946bd932a1cdbdb2b40ad514362bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-11-24T04:53:10Z","title_canon_sha256":"33d2dd8d064275276de07060e8dc0376b4af2d44b7bb24dd0f22b374792512a4"},"schema_version":"1.0","source":{"id":"2411.15715","kind":"arxiv","version":1}},"canonical_sha256":"408874f7f829354a8b7e542ebb0675962a51334974566ba62ea1c50ad0b5525e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"408874f7f829354a8b7e542ebb0675962a51334974566ba62ea1c50ad0b5525e","first_computed_at":"2026-07-05T09:39:39.853990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:39.853990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JD5jBLxTp5HahXrIu9w5OBSLf/McmJ6OFFXd7Gsc88rEg1LSVt4Ra6X6a3p9BuNB04xej0wuxeaTCtgQ3V3iDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:39.854565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04a3b80e33073de0b785ccd38a328cb93f328cd5d391539362860b009af9404d","sha256:1f28468070d405babd90b16ab39fa3f1562f8b12a7c77e1a88d5163346fdbcd9"],"state_sha256":"d59931112ea37649c3958ca5bcfa47a5a9175019e041c77e126e54c9d5651c9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q+HWKnpeOJqYL4pC+pO4iQCu1F58yR4UEJlJQos6N3Tp8xpLmc9Kv50+GcZ8RZCh7YtlOV4U/AJT6b5c0jN6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:30:20.999364Z","bundle_sha256":"da6e0aa6e4377a9ee936da9136b56359ed728aaadbc0b6ecc8af129bfca7a0f6"}}