{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IYLARS3ZWT3IFAESZIFUZIIZQA","short_pith_number":"pith:IYLARS3Z","canonical_record":{"source":{"id":"2411.17651","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-26T18:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"545787f4767aaf2d81de6886ae549066f8663152756146ef4493ab0380194548","abstract_canon_sha256":"1e1eb6efd22ecf86a4b753e5aadc9f67665c1ea8d0aa9de0a3f62c108091592f"},"schema_version":"1.0"},"canonical_sha256":"461608cb79b4f6828092ca0b4ca119803a22a8baae8cf339ab5803f48ba69e1d","source":{"kind":"arxiv","id":"2411.17651","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17651","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17651v2","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17651","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"pith_short_12","alias_value":"IYLARS3ZWT3I","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"pith_short_16","alias_value":"IYLARS3ZWT3IFAES","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"pith_short_8","alias_value":"IYLARS3Z","created_at":"2026-07-05T10:55:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IYLARS3ZWT3IFAESZIFUZIIZQA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17651","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-26T18:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"545787f4767aaf2d81de6886ae549066f8663152756146ef4493ab0380194548","abstract_canon_sha256":"1e1eb6efd22ecf86a4b753e5aadc9f67665c1ea8d0aa9de0a3f62c108091592f"},"schema_version":"1.0"},"canonical_sha256":"461608cb79b4f6828092ca0b4ca119803a22a8baae8cf339ab5803f48ba69e1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:54.078788Z","signature_b64":"Sdk4Eg820hgyh5g6OyoYgHWsbWQYgPiE2LoC35rQyv9a4AX0p1jq9beYyaQ+5HEgTW3I3RhaQvS/q4fbeyw1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"461608cb79b4f6828092ca0b4ca119803a22a8baae8cf339ab5803f48ba69e1d","last_reissued_at":"2026-07-05T10:55:54.078297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:54.078297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17651","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:55:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHA/TgD2k4e9ARWP05DfN8fjuw9gwh5Pay8+kzs7QgYSHH415Gs75x+WTkFp+oyvIpLCgDQoafn/D3rbJAfzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:26:27.748107Z"},"content_sha256":"7ea5e70b841cf7338858c83d91189f187fc3399ede847713cb574d7790fc7e40","schema_version":"1.0","event_id":"sha256:7ea5e70b841cf7338858c83d91189f187fc3399ede847713cb574d7790fc7e40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IYLARS3ZWT3IFAESZIFUZIIZQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Fanny Nina Paravecino, Ronald Pineda, Woosuk Kwon, Yi-Chien Lin","submitted_at":"2024-11-26T18:16:56Z","abstract_excerpt":"Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying parallelism techniques (data, pipeline, tensor) and workload characteristics (e.g., compute-intensive tasks with long prompts vs. memory-intensive tasks with long generation). We propose APEX, an LLM serving system simulator that efficiently identifies optimal parallel execution plans by considering key factors of LLM serving systems, such as memory usage, batching "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17651","kind":"arxiv","version":2},"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/2411.17651/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":"2026-07-05T10:55:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RkfhEKAoJks6U0Go4nQmDPJpxUIkTb00BIAJQI6TF81E1LC3RGPiBwVMp5KDUQEjDa/mbVg7tRFu/PevoWBMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:26:27.748912Z"},"content_sha256":"c3c4a5ce5fdf1e6359cb5a9eac4cb65c42fc266a1dce600028ccd0c218124706","schema_version":"1.0","event_id":"sha256:c3c4a5ce5fdf1e6359cb5a9eac4cb65c42fc266a1dce600028ccd0c218124706"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IYLARS3ZWT3IFAESZIFUZIIZQA/bundle.json","state_url":"https://pith.science/pith/IYLARS3ZWT3IFAESZIFUZIIZQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IYLARS3ZWT3IFAESZIFUZIIZQA/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":"2026-08-03T19:26:27Z","links":{"resolver":"https://pith.science/pith/IYLARS3ZWT3IFAESZIFUZIIZQA","bundle":"https://pith.science/pith/IYLARS3ZWT3IFAESZIFUZIIZQA/bundle.json","state":"https://pith.science/pith/IYLARS3ZWT3IFAESZIFUZIIZQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IYLARS3ZWT3IFAESZIFUZIIZQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IYLARS3ZWT3IFAESZIFUZIIZQA","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":"1e1eb6efd22ecf86a4b753e5aadc9f67665c1ea8d0aa9de0a3f62c108091592f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-26T18:16:56Z","title_canon_sha256":"545787f4767aaf2d81de6886ae549066f8663152756146ef4493ab0380194548"},"schema_version":"1.0","source":{"id":"2411.17651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17651","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17651v2","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17651","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"pith_short_12","alias_value":"IYLARS3ZWT3I","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"pith_short_16","alias_value":"IYLARS3ZWT3IFAES","created_at":"2026-07-05T10:55:54Z"},{"alias_kind":"pith_short_8","alias_value":"IYLARS3Z","created_at":"2026-07-05T10:55:54Z"}],"graph_snapshots":[{"event_id":"sha256:c3c4a5ce5fdf1e6359cb5a9eac4cb65c42fc266a1dce600028ccd0c218124706","target":"graph","created_at":"2026-07-05T10:55:54Z","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/2411.17651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying parallelism techniques (data, pipeline, tensor) and workload characteristics (e.g., compute-intensive tasks with long prompts vs. memory-intensive tasks with long generation). We propose APEX, an LLM serving system simulator that efficiently identifies optimal parallel execution plans by considering key factors of LLM serving systems, such as memory usage, batching ","authors_text":"Fanny Nina Paravecino, Ronald Pineda, Woosuk Kwon, Yi-Chien Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-26T18:16:56Z","title":"APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17651","kind":"arxiv","version":2},"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":"sha256:7ea5e70b841cf7338858c83d91189f187fc3399ede847713cb574d7790fc7e40","target":"record","created_at":"2026-07-05T10:55:54Z","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":"1e1eb6efd22ecf86a4b753e5aadc9f67665c1ea8d0aa9de0a3f62c108091592f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-26T18:16:56Z","title_canon_sha256":"545787f4767aaf2d81de6886ae549066f8663152756146ef4493ab0380194548"},"schema_version":"1.0","source":{"id":"2411.17651","kind":"arxiv","version":2}},"canonical_sha256":"461608cb79b4f6828092ca0b4ca119803a22a8baae8cf339ab5803f48ba69e1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"461608cb79b4f6828092ca0b4ca119803a22a8baae8cf339ab5803f48ba69e1d","first_computed_at":"2026-07-05T10:55:54.078297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:54.078297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sdk4Eg820hgyh5g6OyoYgHWsbWQYgPiE2LoC35rQyv9a4AX0p1jq9beYyaQ+5HEgTW3I3RhaQvS/q4fbeyw1Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:54.078788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ea5e70b841cf7338858c83d91189f187fc3399ede847713cb574d7790fc7e40","sha256:c3c4a5ce5fdf1e6359cb5a9eac4cb65c42fc266a1dce600028ccd0c218124706"],"state_sha256":"83044717cdb95bc4db0aa10f8903ef1dd2198871ce8e98fd5816277e85fbdcd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IXzYEvwy/b07XyyiUnfM+XCwfeYGWNrGDWFIQKDBgfDDugA/NWHJZrV9Zi4T2fku1TJMQOyMLsEWIKK9LbxxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:26:27.753825Z","bundle_sha256":"289a2528aababb66b23e1843f11a86f538714523d777005ae3a7c3484b20aa0f"}}