{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FITYQVD5QZSOUHB7VEF6VNW6JU","short_pith_number":"pith:FITYQVD5","canonical_record":{"source":{"id":"2506.21901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-27T04:38:20Z","cross_cats_sorted":[],"title_canon_sha256":"4f658baa0063283ef84fec5914b5f6b7b7f576c004f8e4cea18658c96cf9c2d1","abstract_canon_sha256":"42b6088145ed58d70cc4876b3e6112706d3aedfc9afb38590c6f823f9194d7d9"},"schema_version":"1.0"},"canonical_sha256":"2a2788547d8664ea1c3fa90beab6de4d37a02a188d9f90ea1c13014dc19e907a","source":{"kind":"arxiv","id":"2506.21901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21901","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21901v1","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21901","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"FITYQVD5QZSO","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"FITYQVD5QZSOUHB7","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"FITYQVD5","created_at":"2026-07-05T11:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FITYQVD5QZSOUHB7VEF6VNW6JU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-27T04:38:20Z","cross_cats_sorted":[],"title_canon_sha256":"4f658baa0063283ef84fec5914b5f6b7b7f576c004f8e4cea18658c96cf9c2d1","abstract_canon_sha256":"42b6088145ed58d70cc4876b3e6112706d3aedfc9afb38590c6f823f9194d7d9"},"schema_version":"1.0"},"canonical_sha256":"2a2788547d8664ea1c3fa90beab6de4d37a02a188d9f90ea1c13014dc19e907a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:03.709966Z","signature_b64":"F7DpEqZNYn+pJrHwToVBg73YyTVcRytZYRice8kLbLcgEzoJNfZnHl5fdST1No5xXuYuIZEin2nWkLf3ZIyNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2788547d8664ea1c3fa90beab6de4d37a02a188d9f90ea1c13014dc19e907a","last_reissued_at":"2026-07-05T11:28:03.709499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:03.709499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21901","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":"2026-07-05T11:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2/WQmexVwDxBUGyIlIxnZhbA3X4XnnwpC7W8QYU7Zshc/PVFvi+0OQmOmTSRew1nF5mScbqFNMPG40mRtJMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:39:54.933866Z"},"content_sha256":"4f434cc418160d3cd7cfff278b603baddfaafaea9b5eeb9488ab32fe9ad23516","schema_version":"1.0","event_id":"sha256:4f434cc418160d3cd7cfff278b603baddfaafaea9b5eeb9488ab32fe9ad23516"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FITYQVD5QZSOUHB7VEF6VNW6JU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of LLM Inference Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Guoliang Li, James Pan","submitted_at":"2025-06-27T04:38:20Z","abstract_excerpt":"The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the unique autoregressive nature of LLM request processing, motivating new techniques for achieving high performance while preserving high inference quality over high-volume and high-velocity workloads. While many of these techniques are discussed across the literature, they have not been analyzed under the framework of a complete inference system, nor have the syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21901","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/2506.21901/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":"2026-07-05T11:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQQb/BIJQ712irUccbKchEU82JG/IdpYPps1/IyIvOVFw4mYMpstRDyZbRL69c3aHLO8STKSdq47fTFwdlItDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:39:54.934424Z"},"content_sha256":"61b83a991383ed4ac8d03731c4ebdaa07637792b409e5dd6919eb42b25db9727","schema_version":"1.0","event_id":"sha256:61b83a991383ed4ac8d03731c4ebdaa07637792b409e5dd6919eb42b25db9727"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FITYQVD5QZSOUHB7VEF6VNW6JU/bundle.json","state_url":"https://pith.science/pith/FITYQVD5QZSOUHB7VEF6VNW6JU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FITYQVD5QZSOUHB7VEF6VNW6JU/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":"2026-08-08T09:39:54Z","links":{"resolver":"https://pith.science/pith/FITYQVD5QZSOUHB7VEF6VNW6JU","bundle":"https://pith.science/pith/FITYQVD5QZSOUHB7VEF6VNW6JU/bundle.json","state":"https://pith.science/pith/FITYQVD5QZSOUHB7VEF6VNW6JU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FITYQVD5QZSOUHB7VEF6VNW6JU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FITYQVD5QZSOUHB7VEF6VNW6JU","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":"42b6088145ed58d70cc4876b3e6112706d3aedfc9afb38590c6f823f9194d7d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-27T04:38:20Z","title_canon_sha256":"4f658baa0063283ef84fec5914b5f6b7b7f576c004f8e4cea18658c96cf9c2d1"},"schema_version":"1.0","source":{"id":"2506.21901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21901","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21901v1","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21901","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"FITYQVD5QZSO","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"FITYQVD5QZSOUHB7","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"FITYQVD5","created_at":"2026-07-05T11:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:61b83a991383ed4ac8d03731c4ebdaa07637792b409e5dd6919eb42b25db9727","target":"graph","created_at":"2026-07-05T11:28:03Z","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/2506.21901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the unique autoregressive nature of LLM request processing, motivating new techniques for achieving high performance while preserving high inference quality over high-volume and high-velocity workloads. While many of these techniques are discussed across the literature, they have not been analyzed under the framework of a complete inference system, nor have the syst","authors_text":"Guoliang Li, James Pan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-27T04:38:20Z","title":"A Survey of LLM Inference Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21901","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":"sha256:4f434cc418160d3cd7cfff278b603baddfaafaea9b5eeb9488ab32fe9ad23516","target":"record","created_at":"2026-07-05T11:28:03Z","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":"42b6088145ed58d70cc4876b3e6112706d3aedfc9afb38590c6f823f9194d7d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-06-27T04:38:20Z","title_canon_sha256":"4f658baa0063283ef84fec5914b5f6b7b7f576c004f8e4cea18658c96cf9c2d1"},"schema_version":"1.0","source":{"id":"2506.21901","kind":"arxiv","version":1}},"canonical_sha256":"2a2788547d8664ea1c3fa90beab6de4d37a02a188d9f90ea1c13014dc19e907a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a2788547d8664ea1c3fa90beab6de4d37a02a188d9f90ea1c13014dc19e907a","first_computed_at":"2026-07-05T11:28:03.709499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:03.709499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F7DpEqZNYn+pJrHwToVBg73YyTVcRytZYRice8kLbLcgEzoJNfZnHl5fdST1No5xXuYuIZEin2nWkLf3ZIyNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:03.709966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f434cc418160d3cd7cfff278b603baddfaafaea9b5eeb9488ab32fe9ad23516","sha256:61b83a991383ed4ac8d03731c4ebdaa07637792b409e5dd6919eb42b25db9727"],"state_sha256":"816bd1a54b79852247b365aa05e34b0d52857051be6808801dbba53dbbb13647"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32Jn8cWSPnTBS/yMqXIoLxvkfCZEv/eOgQlho9vL/vizn0y5PAWXrTU1CrL8RZnemeL+HCPA/tIlXg82pcY6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:39:54.938148Z","bundle_sha256":"f46127c66ca26571daae42fdfb31b7fefb9ab7709ced81ad134efa0059907d83"}}