neuron-tai/.scratch/distributed-gguf-runtime/issues/069-prepare-narrow-upstream-llama-cpp-collaboration-patches.md

DGR-069: Prepare narrow upstream llama.cpp collaboration patches

• Status / triage: specification only; ready-for-human; passes: false
• Execution mode: HITL
• Milestone: M5
• Dependencies: DGR-028, DGR-035, DGR-038, DGR-051
• Blocks (derived): DGR-071
• Labels: area:upstream, area:patches, type:collaboration, priority:p2, gate:hitl, ready-for-human
• Evidence class: release
• Hardware: none
• Model: generic+deepseek-v4
• Upstream: yes

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/069-prepare-narrow-upstream-llama-cpp-collaboration-patches.md, and evidence READMEs for dependencies (DGR-028, DGR-035, DGR-038, DGR-051) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Reduce long-term patch burden through generic upstreamable hooks without asking llama.cpp to own Meshnet.

Acceptance criteria

• Separate generic range loading, boundary I/O, and filtered state hooks from project worker/protocol code.
• Provide one scoped patch, focused test, and minimal reproducer per concern against the exact upstream pin.
• Compare the proposal with prior-art evidence and current upstream V4 support/maturity.
• Prepare human-ready design/outreach text; actual issue/PR submission remains a human action.
• 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-069/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.