{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CYQSKMLJ7Q44Z3VKXBMP5OAESZ","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":"1d33634277a676123bf0abc09f0f5821ab1b891ea8f0bfe24d9e7fe4d255f3c5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-01T08:58:23Z","title_canon_sha256":"240fb490009746a9e7f76983c8e6e9e308c6d738c8431cf64a131e846f093cfb"},"schema_version":"1.0","source":{"id":"2606.01927","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01927","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01927v1","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01927","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"CYQSKMLJ7Q44","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"CYQSKMLJ7Q44Z3VK","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"CYQSKMLJ","created_at":"2026-06-02T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:e4e10d1c28002f70bfe180a6d09684a10e3ddcd799bab33324d83e0a74810d9c","target":"graph","created_at":"2026-06-02T02:05:00Z","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/2606.01927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deployers of online LLM services usually seek to maximize cluster-wide performance given a fixed number of GPUs. Tensor parallelism (TP) is necessary to fit modern models but scales sub-linearly as the TP degree t grows, due to cross-GPU communication and non-scalable runtime work, as predicted by Amdahl's Law. Conversely, increasing t improves memory efficiency and alleviates KV-cache contention and swapping. We identify and validate an empirical optimal TP degree t_e that balances these effects. We present Albireo, a parallel inference system that raises the attainable t_e by shrinking the n","authors_text":"Alan Zhao, Cyril Y. He, Wei Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-01T08:58:23Z","title":"Scaling LLM Inference Beyond Amdahl`s Limits via Eliminating Non-Scalable Overheads"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01927","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":"sha256:143f7481783eeb36e3e81e270d571dea55e57b567457803dee6fc9991a270daf","target":"record","created_at":"2026-06-02T02:05:00Z","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":"1d33634277a676123bf0abc09f0f5821ab1b891ea8f0bfe24d9e7fe4d255f3c5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-01T08:58:23Z","title_canon_sha256":"240fb490009746a9e7f76983c8e6e9e308c6d738c8431cf64a131e846f093cfb"},"schema_version":"1.0","source":{"id":"2606.01927","kind":"arxiv","version":1}},"canonical_sha256":"1621253169fc39cceeaab858feb804964e72530ccc0e11b6c566073906b1fa19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1621253169fc39cceeaab858feb804964e72530ccc0e11b6c566073906b1fa19","first_computed_at":"2026-06-02T02:05:00.748980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:00.748980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cogRO6d4FWfyOjDpkYI/Xu+GsFUCixhbeD8qqIvRb3pmOoYLKi8D37dwLoHsI11fpNefxU5hA3u255hwwDYhCA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:00.749388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01927","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:143f7481783eeb36e3e81e270d571dea55e57b567457803dee6fc9991a270daf","sha256:e4e10d1c28002f70bfe180a6d09684a10e3ddcd799bab33324d83e0a74810d9c"],"state_sha256":"117fd001ae3e8a70660a41f0b15dfd87d4f5f7e1b46644e2dc4b43698c4b4370"}