{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OSLC2BGJH2RS37OBAU3BKVL75Z","short_pith_number":"pith:OSLC2BGJ","canonical_record":{"source":{"id":"2409.06646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-09-10T17:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"31883354e2b522a892a88507f6733b4c6795129929d7e4a288b0a14e85710ed6","abstract_canon_sha256":"b57c87485974cd149a96b44e14e84bf474b44b47754e1f3736f0038aaf352e17"},"schema_version":"1.0"},"canonical_sha256":"74962d04c93ea32dfdc1053615557fee5f30c9f2ac380e735611a2428531ffc8","source":{"kind":"arxiv","id":"2409.06646","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06646","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06646v1","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06646","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"OSLC2BGJH2RS","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"OSLC2BGJH2RS37OB","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"OSLC2BGJ","created_at":"2026-07-05T09:05:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OSLC2BGJH2RS37OBAU3BKVL75Z","target":"record","payload":{"canonical_record":{"source":{"id":"2409.06646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-09-10T17:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"31883354e2b522a892a88507f6733b4c6795129929d7e4a288b0a14e85710ed6","abstract_canon_sha256":"b57c87485974cd149a96b44e14e84bf474b44b47754e1f3736f0038aaf352e17"},"schema_version":"1.0"},"canonical_sha256":"74962d04c93ea32dfdc1053615557fee5f30c9f2ac380e735611a2428531ffc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:27.606142Z","signature_b64":"VtHu4JeEOUAGMIoTFH+TRjgKMtxdiClvAT9JPB1T2jO2MhhJI+SfggsJ3W9TWnph3oWqXzajo9r3DsWUSY98DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74962d04c93ea32dfdc1053615557fee5f30c9f2ac380e735611a2428531ffc8","last_reissued_at":"2026-07-05T09:05:27.605669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:27.605669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.06646","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":"2026-07-05T09:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/y/vczsc+hxE848ztP5LrtDOd/211jo9R5aB/psXspzMqQ6s4JzBrv/juRvHnf/K5PLnz2oKBGwoH97cxOLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T08:27:03.730206Z"},"content_sha256":"1dd80a4e367a3cfa9a75c17bb473445b2df3385809befd5b0d05a54e107bcbaf","schema_version":"1.0","event_id":"sha256:1dd80a4e367a3cfa9a75c17bb473445b2df3385809befd5b0d05a54e107bcbaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OSLC2BGJH2RS37OBAU3BKVL75Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Workload Placement on Multi-Instance GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bekir Turkkan, Chandra Narayanaswami, Gerard Vanloo, Pavankumar Murali, Pavithra Harsha, Rohan Arora","submitted_at":"2024-09-10T17:05:11Z","abstract_excerpt":"There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of GPUs support a partitioning feature, called Multi-Instance GPU (MIG) to allow multiple workloads to share a GPU, albeit with some constraints. In this paper we investigate how to optimize the placement of Large Language Model (LLM)-based AI Inferencing workloads on GPUs. We first identify and present several use cases that are encountered in practice that requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06646","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/2409.06646/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":"2026-07-05T09:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DtVseYbQn+RC0/UBfy0TbHEiw7wlWjFXJGF+Bjj8sS2+P0iHa8X0Wn7mOe6vo4prhe1dCj0lSDiQHKyLLiBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T08:27:03.730586Z"},"content_sha256":"848b174d0a495ed25d681675bf2ab04616f4102e0346299e7815cf07fdf7ff6c","schema_version":"1.0","event_id":"sha256:848b174d0a495ed25d681675bf2ab04616f4102e0346299e7815cf07fdf7ff6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSLC2BGJH2RS37OBAU3BKVL75Z/bundle.json","state_url":"https://pith.science/pith/OSLC2BGJH2RS37OBAU3BKVL75Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSLC2BGJH2RS37OBAU3BKVL75Z/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":"2026-07-27T08:27:03Z","links":{"resolver":"https://pith.science/pith/OSLC2BGJH2RS37OBAU3BKVL75Z","bundle":"https://pith.science/pith/OSLC2BGJH2RS37OBAU3BKVL75Z/bundle.json","state":"https://pith.science/pith/OSLC2BGJH2RS37OBAU3BKVL75Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSLC2BGJH2RS37OBAU3BKVL75Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OSLC2BGJH2RS37OBAU3BKVL75Z","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":"b57c87485974cd149a96b44e14e84bf474b44b47754e1f3736f0038aaf352e17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-09-10T17:05:11Z","title_canon_sha256":"31883354e2b522a892a88507f6733b4c6795129929d7e4a288b0a14e85710ed6"},"schema_version":"1.0","source":{"id":"2409.06646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06646","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06646v1","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06646","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"OSLC2BGJH2RS","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"OSLC2BGJH2RS37OB","created_at":"2026-07-05T09:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"OSLC2BGJ","created_at":"2026-07-05T09:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:848b174d0a495ed25d681675bf2ab04616f4102e0346299e7815cf07fdf7ff6c","target":"graph","created_at":"2026-07-05T09:05:27Z","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/2409.06646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of GPUs support a partitioning feature, called Multi-Instance GPU (MIG) to allow multiple workloads to share a GPU, albeit with some constraints. In this paper we investigate how to optimize the placement of Large Language Model (LLM)-based AI Inferencing workloads on GPUs. We first identify and present several use cases that are encountered in practice that requ","authors_text":"Bekir Turkkan, Chandra Narayanaswami, Gerard Vanloo, Pavankumar Murali, Pavithra Harsha, Rohan Arora","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-09-10T17:05:11Z","title":"Optimal Workload Placement on Multi-Instance GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06646","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":"sha256:1dd80a4e367a3cfa9a75c17bb473445b2df3385809befd5b0d05a54e107bcbaf","target":"record","created_at":"2026-07-05T09:05:27Z","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":"b57c87485974cd149a96b44e14e84bf474b44b47754e1f3736f0038aaf352e17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-09-10T17:05:11Z","title_canon_sha256":"31883354e2b522a892a88507f6733b4c6795129929d7e4a288b0a14e85710ed6"},"schema_version":"1.0","source":{"id":"2409.06646","kind":"arxiv","version":1}},"canonical_sha256":"74962d04c93ea32dfdc1053615557fee5f30c9f2ac380e735611a2428531ffc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74962d04c93ea32dfdc1053615557fee5f30c9f2ac380e735611a2428531ffc8","first_computed_at":"2026-07-05T09:05:27.605669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:27.605669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VtHu4JeEOUAGMIoTFH+TRjgKMtxdiClvAT9JPB1T2jO2MhhJI+SfggsJ3W9TWnph3oWqXzajo9r3DsWUSY98DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:27.606142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dd80a4e367a3cfa9a75c17bb473445b2df3385809befd5b0d05a54e107bcbaf","sha256:848b174d0a495ed25d681675bf2ab04616f4102e0346299e7815cf07fdf7ff6c"],"state_sha256":"ae1c4531651090b5d585ebb636ec8ede7cc957a55e9bac15cca48627ea2d121f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pXLdH4oo3JYm7W7BGOeIMyR1Bi4nKpOwAu8PhgHfssp5KdWbgjcthn6ujpbOSesiuUz6F0twNDzRu+RYzu47Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T08:27:03.732650Z","bundle_sha256":"60270d7ab4a181afcf6d3429a34bff866dfc287b74e319be7991d74a1d5d564e"}}