{
  "url": "https://appliedfrontier.nl/en/research/signal-54d715cb36a72fdf/",
  "title": "DolphinRouting: Cluster-Level Binary Routing for Disaggregated LLM Inference Serving",
  "published": "2026-10-29",
  "excerpt": "Prefill-decode (PD) disaggregation isolates the two phases of large language model serving, but request-level path selection must account for prefill work, cache reuse, and decode",
  "content_sha256": "731e362e242efbc047ea9a1ecb228c717495e078fb4f06962cf2795bcd76c841",
  "extracted_chars": 866,
  "artifact_links": [
    "https://arxiv.org/abs/2610.40292"
  ],
  "arxiv_id": "2610.40292",
  "extraction_scope": "preprint_abstract_metadata",
  "full_text_available": false,
  "id": "signal-54d715cb36a72fdf",
  "org": "Research community",
  "topic": "Compute & efficiency",
  "source_kind": "preprint",
  "status": "unreviewed-source-report",
  "analysis_method": "deterministic_research_triage_v2",
  "novelty_verified": false,
  "proof_checked": false,
  "peer_review_verified": false,
  "matched_terms": [
    "Compute & efficiency"
  ],
  "checked_at": "2026-10-31T19:32:55+00:00",
  "first_seen": "2026-10-31T19:32:55+00:00",
  "source_hash": "06050ca8001e1cb52d85d3a88cdebd2755c195cb6f181b271e8d9b0e5157cf16",
  "source_url": "https://arxiv.org/abs/2610.40292",
  "language": "en",
  "indexing": "noindex_until_editorially_enriched"
}