{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7VEVUDZIFT6EBQPQ7TFM6NBUN2","short_pith_number":"pith:7VEVUDZI","canonical_record":{"source":{"id":"2403.01136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T08:40:07Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"9cd455745d7c87e27e46f2367044a28d2a72f997cbc38dcb2d7041be726db762","abstract_canon_sha256":"4d6ea7bebe02032945a75c5c3fce431e6fc95cba4a3931389dc614df257dc68c"},"schema_version":"1.0"},"canonical_sha256":"fd495a0f282cfc40c1f0fccacf34346eb5d3b7160dd05397f62e3ba2f767d857","source":{"kind":"arxiv","id":"2403.01136","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01136","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01136v1","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01136","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"pith_short_12","alias_value":"7VEVUDZIFT6E","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"pith_short_16","alias_value":"7VEVUDZIFT6EBQPQ","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"pith_short_8","alias_value":"7VEVUDZI","created_at":"2026-07-05T07:51:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7VEVUDZIFT6EBQPQ7TFM6NBUN2","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T08:40:07Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"9cd455745d7c87e27e46f2367044a28d2a72f997cbc38dcb2d7041be726db762","abstract_canon_sha256":"4d6ea7bebe02032945a75c5c3fce431e6fc95cba4a3931389dc614df257dc68c"},"schema_version":"1.0"},"canonical_sha256":"fd495a0f282cfc40c1f0fccacf34346eb5d3b7160dd05397f62e3ba2f767d857","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:16.935722Z","signature_b64":"mGY+Ljcq7hl0oj11neXK9Rf00T6+pgG2GIWl6oowPwCcV1SI77apMIIYQ6IG1SgkbhnziSH02TR+t8aK91O2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd495a0f282cfc40c1f0fccacf34346eb5d3b7160dd05397f62e3ba2f767d857","last_reissued_at":"2026-07-05T07:51:16.935363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:16.935363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01136","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":"2026-07-05T07:51:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zhcxvj2uP5g9btHXLbugK7/ipCMDKH0N8P0zYIKI0javpsanhr/S18CjfO/nNoBs0bO/cG/jZDAo4Ga4SSnwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:37.367637Z"},"content_sha256":"14579b55905307729de457b830c7b2df902348436425d1a1de01586019749659","schema_version":"1.0","event_id":"sha256:14579b55905307729de457b830c7b2df902348436425d1a1de01586019749659"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7VEVUDZIFT6EBQPQ7TFM6NBUN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Borui Wan, Chuan Wu, Haibin Lin, Juntao Zhao, Yanghua Peng","submitted_at":"2024-03-02T08:40:07Z","abstract_excerpt":"Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are largely served using uniform high-caliber GPUs nowadays, utilizing a heterogeneous cluster with a mix of available high- and low-capacity GPUs can potentially substantially reduce the serving cost. There is a lack of designs to support efficient LLM serving using a heterogeneous cluster, while the current solutions focus on model partition and uniform compressi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01136","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/2403.01136/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":"2026-07-05T07:51:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LGaqWD6U1zlMLBMDwfPUgsMKwM8jMb6rn/JPqsxsWwdbSIL6oak+fBQXSRJLnmfYUxCnyoF40/4ebFECbyK+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:37.368177Z"},"content_sha256":"ff8ecfe5f53325e6149cc1f5a7d7d40e5c7c32e23309c946033ef46850dd3382","schema_version":"1.0","event_id":"sha256:ff8ecfe5f53325e6149cc1f5a7d7d40e5c7c32e23309c946033ef46850dd3382"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2/bundle.json","state_url":"https://pith.science/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2/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":"2026-08-05T07:13:37Z","links":{"resolver":"https://pith.science/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2","bundle":"https://pith.science/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2/bundle.json","state":"https://pith.science/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VEVUDZIFT6EBQPQ7TFM6NBUN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7VEVUDZIFT6EBQPQ7TFM6NBUN2","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":"4d6ea7bebe02032945a75c5c3fce431e6fc95cba4a3931389dc614df257dc68c","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T08:40:07Z","title_canon_sha256":"9cd455745d7c87e27e46f2367044a28d2a72f997cbc38dcb2d7041be726db762"},"schema_version":"1.0","source":{"id":"2403.01136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01136","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01136v1","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01136","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"pith_short_12","alias_value":"7VEVUDZIFT6E","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"pith_short_16","alias_value":"7VEVUDZIFT6EBQPQ","created_at":"2026-07-05T07:51:16Z"},{"alias_kind":"pith_short_8","alias_value":"7VEVUDZI","created_at":"2026-07-05T07:51:16Z"}],"graph_snapshots":[{"event_id":"sha256:ff8ecfe5f53325e6149cc1f5a7d7d40e5c7c32e23309c946033ef46850dd3382","target":"graph","created_at":"2026-07-05T07:51:16Z","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/2403.01136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are largely served using uniform high-caliber GPUs nowadays, utilizing a heterogeneous cluster with a mix of available high- and low-capacity GPUs can potentially substantially reduce the serving cost. There is a lack of designs to support efficient LLM serving using a heterogeneous cluster, while the current solutions focus on model partition and uniform compressi","authors_text":"Borui Wan, Chuan Wu, Haibin Lin, Juntao Zhao, Yanghua Peng","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T08:40:07Z","title":"LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01136","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":"sha256:14579b55905307729de457b830c7b2df902348436425d1a1de01586019749659","target":"record","created_at":"2026-07-05T07:51:16Z","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":"4d6ea7bebe02032945a75c5c3fce431e6fc95cba4a3931389dc614df257dc68c","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T08:40:07Z","title_canon_sha256":"9cd455745d7c87e27e46f2367044a28d2a72f997cbc38dcb2d7041be726db762"},"schema_version":"1.0","source":{"id":"2403.01136","kind":"arxiv","version":1}},"canonical_sha256":"fd495a0f282cfc40c1f0fccacf34346eb5d3b7160dd05397f62e3ba2f767d857","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd495a0f282cfc40c1f0fccacf34346eb5d3b7160dd05397f62e3ba2f767d857","first_computed_at":"2026-07-05T07:51:16.935363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:16.935363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mGY+Ljcq7hl0oj11neXK9Rf00T6+pgG2GIWl6oowPwCcV1SI77apMIIYQ6IG1SgkbhnziSH02TR+t8aK91O2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:16.935722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14579b55905307729de457b830c7b2df902348436425d1a1de01586019749659","sha256:ff8ecfe5f53325e6149cc1f5a7d7d40e5c7c32e23309c946033ef46850dd3382"],"state_sha256":"381ad7ccbae44e0bcaecc1b864794c4aebb0c536c0b617daaf1f6f007c56b4c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNRaoYzSivSJikkY8MgqG8Tnain5asIHwvwEs/grTMMsfab5Js+pMowjRecnU02nUOZIFBvBVsTGAZURJUyOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:13:37.372134Z","bundle_sha256":"20d9904fa68200f2c8662f47ac425ce11db206f18160423fc2f881a82c96f932"}}