neuron-tai/.scratch/distributed-gguf-runtime/issues/045-inventory-v4-gguf-tensors-and-layer-ownership.md

DGR-045: Inventory V4 GGUF tensors and layer ownership

• Status / triage: specification only; ready-for-agent; passes: false
• Execution mode: AFK
• Milestone: M3
• Dependencies: DGR-026, DGR-044
• Blocks (derived): DGR-046, DGR-047, DGR-050
• Labels: area:deepseek-v4, area:weights, type:research-spike, priority:p0, ready-for-agent
• Evidence class: real-model
• Hardware: none
• Model: deepseek-v4-flash
• Upstream: yes

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/045-inventory-v4-gguf-tensors-and-layer-ownership.md, and evidence READMEs for dependencies (DGR-026, DGR-044) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Derive exact head, repeated-layer, tail, expert, auxiliary-state, and MTP ownership from the pinned artifact.

Acceptance criteria

• Produce a machine-readable inventory tied to the target SHA and exact GGUF artifact.
• Classify embeddings, 43 main layers, final head, MTP, mHC, attention variants, indexer/compressor, and MoE tensors.
• Validate half-open range ownership and fail on unclassified required tensors.
• Inventory tooling works across quants without embedding quant names in architecture logic.
• Applicable shared quality gates in prd.json pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.

Shared quality gates

• Targeted deterministic tests pass; Python changes also pass python -m compileall packages tests.
• git diff --check passes.
• Default tests are model-download-free, API-credit-free, and GPU-free.
• Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
• Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
• Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never /home.
• Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.

Evidence handoff

Write and verify .scratch/distributed-gguf-runtime/evidence/DGR-045/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.