{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F6FNTHPETU6TQGP543TU7MTZ4B","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":"d2cc89bef93f5d07586fa0b225327f80b5340731dc27537c01087e8ef22801e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-07T13:46:21Z","title_canon_sha256":"cabc253e34593da69c3f430220a92819ae5522891e146abd3703433570083456"},"schema_version":"1.0","source":{"id":"2504.08791","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08791","created_at":"2026-07-07T02:17:06Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08791v3","created_at":"2026-07-07T02:17:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08791","created_at":"2026-07-07T02:17:06Z"},{"alias_kind":"pith_short_12","alias_value":"F6FNTHPETU6T","created_at":"2026-07-07T02:17:06Z"},{"alias_kind":"pith_short_16","alias_value":"F6FNTHPETU6TQGP5","created_at":"2026-07-07T02:17:06Z"},{"alias_kind":"pith_short_8","alias_value":"F6FNTHPE","created_at":"2026-07-07T02:17:06Z"}],"graph_snapshots":[{"event_id":"sha256:b741ccf52d5d7da4c022c7c5ec5a71fb188c9c31bbbe215466dc0ce0227d0530","target":"graph","created_at":"2026-07-07T02:17:06Z","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/2504.08791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability. To overcome this challenge, we present prima.cpp, a distributed on-device inference system that runs 30-70B LLMs on consumer home clusters with mixed CPUs/GPUs, insufficient RAM/VRAM, slow disks, Wi-Fi links, and heterogeneous OSs. We introduce pipelined-ring parallelism (PRP) to overlap disk I/O with compute and communication, and address the prefetch-release conflict in mmap-based offloading. We further propose Halda, a heteroge","authors_text":"Hongfang Yu, Hong Huang, Jianshu She, Mohsen Guizani, Qirong Ho, Rongxing Xiao, Tao Li, Wei Xiang, Wenjiao Feng, Xue Liu, Zonghang Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-07T13:46:21Z","title":"Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08791","kind":"arxiv","version":3},"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:cd98ced60123f73b5af22d28d0ac392863bcdbd20d2007e3724ebe383d34f363","target":"record","created_at":"2026-07-07T02:17:06Z","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":"d2cc89bef93f5d07586fa0b225327f80b5340731dc27537c01087e8ef22801e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-07T13:46:21Z","title_canon_sha256":"cabc253e34593da69c3f430220a92819ae5522891e146abd3703433570083456"},"schema_version":"1.0","source":{"id":"2504.08791","kind":"arxiv","version":3}},"canonical_sha256":"2f8ad99de49d3d3819fde6e74fb279e05ad5c2c65b27b1af9603a0914d5c3457","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f8ad99de49d3d3819fde6e74fb279e05ad5c2c65b27b1af9603a0914d5c3457","first_computed_at":"2026-07-07T02:17:06.860809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:06.860809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xyXwa6RY7kf36OwyUR+hdOZDM2UOcj8Fqm22oaKkeoPIZ+kX+nQafE3ROCEUkc/BUsow3ADI/iVe1HYLcrAZBw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:06.862021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08791","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd98ced60123f73b5af22d28d0ac392863bcdbd20d2007e3724ebe383d34f363","sha256:b741ccf52d5d7da4c022c7c5ec5a71fb188c9c31bbbe215466dc0ce0227d0530"],"state_sha256":"0d6aec44abf07506d2d0197da70f227afc9c1099faf0cbb2e3e29eaf07ac0446"}