neuron-tai/.scratch/distributed-gguf-runtime/issues/067-certify-the-backend-capability-matrix.md

DGR-067: Certify the backend capability matrix

• Status / triage: specification only; ready-for-human; passes: false
• Execution mode: HITL
• Milestone: M4
• Dependencies: DGR-030, DGR-053, DGR-062, DGR-066
• Blocks (derived): DGR-068, DGR-070
• Labels: area:hardware, area:admission, type:certification, priority:p1, gate:hitl, ready-for-human
• Evidence class: real-hardware
• Hardware: required
• 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/067-certify-the-backend-capability-matrix.md, and evidence READMEs for dependencies (DGR-030, DGR-053, DGR-062, DGR-066) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Publish only backend/model/recipe lanes proven on actual CPU, CUDA, ROCm, Vulkan, or Metal hardware.

Acceptance criteria

• Maintain independent build and certification status for CPU, CUDA, ROCm, Vulkan, and Metal.
• Each advertised lane includes real hardware/driver/runtime/model evidence for parity, concurrency, cancellation, cleanup, and useful speed.
• Build success alone never makes a lane routable; unavailable hardware remains explicitly dark.
• Tracker admission consumes signed/versioned certification records rather than backend-name allowlists.
• Mixed-backend routes require exact compatibility evidence and fail closed otherwise.
• 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-067/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.