4.2 KiB
4.2 KiB
18 — Certify whole-model GLM-5.2 runtime semantics
Status: ready-for-agent
Mandatory fresh-session context
- Read RALPH-CONTEXT.md, GLM-5.2-MAX-ALPHA-ROADMAP.md, and this issue completely before changing code.
- This issue is
DGR-018in prd.json. - Read and verify every dependency evidence README.
- Inspect current upstream behavior and
git status; community claims that a model “works” are not correctness evidence.
Description
As a runtime maintainer, I need a certified whole-model oracle for the exact lowest-quant GLM-5.2 artifact so that distributed parity is measured against correct MoE, DSA, IndexShare, cache, and Max-template semantics.
Expected durable outputs
- Verified target artifact on mounted storage
- Stock-pin baseline and warning/tensor inventory
- Focused GLM runtime correctness tests and minimum patch series, if required
- Signed whole-model oracle recipe, deterministic outputs, metrics, and limitations
evidence/DGR-018/README.md
Acceptance criteria
- Preflight a 256-GiB-class reference host with at least 224 GiB runtime-accessible memory after OS reservation and approximately 250 GB free mounted storage; abort before download if storage resolves under
/homeor requirements are unmet. - Configure the oracle's alpha lane for 16,384 context, concurrency 1, and Q8_0 MLA/indexer KV; record actual MLA, indexer-cache, scratch, and peak resident allocations separately.
- Download/resume and verify all six DGR-017
UD-IQ1_Sfiles against exact sizes and LFS SHA-256 values. - Load the target with the unmodified DGR-004 pin first and retain full logs, tensor warnings, peak memory, context/KV allocation, TTFT, and decode timing.
- Prove from graph/runtime evidence whether 256-expert MoE/top-8/shared expert, DSA lightning indexer/sparse attention, IndexShare Full/Shared reuse, and
reasoning_effort=maxare active. - Dense-attention or replicated-indexer compatibility fallback is labeled incomplete and cannot become the oracle solely because it emits plausible text.
- Audit focused upstream/Mesh-LLM donor tests and patches; adopt or rewrite only independently understood minimum changes and record provenance/rejection rationale.
- Handle the trailing NextN/MTP tensors explicitly; MTP may remain disabled for alpha, but ignored tensors and layer-count behavior must be understood and tested.
- Run deterministic prefill/greedy decode and fixed Max-mode coding, structured-output/tool-call, and reasoning sentinels; retain raw prompts, outputs, token IDs, and compared state/logit evidence.
- Bind the oracle to exact artifact, tokenizer/template, adapter, backend class, compute/activation/KV dtypes, context/RoPE, llama.cpp commit, and patch-series hash.
- Produce a signed
passorstopsemantic-runtime verdict; no performance threshold is weakened after execution. - Targeted native/unit tests and clean pinned rebuild pass.
git diff --checkpasses.- Default tests remain model-download-free/GPU-free; full-target execution is opt-in and never runs in default CI.
- Model artifacts and caches remain on configured mounted-drive storage and never under
/home. - Preserve all pre-existing working-tree changes and stage only files belonging to this story.
- Write
evidence/DGR-018/README.mdwith exact hardware, storage, source revisions, files, commands, raw-result paths, real results, limitations, and handoff. - Update only this story issue to
Status: doneafter every acceptance criterion passes.
Dependency handoff
DGR-003,DGR-004, andDGR-017must havepasses: true; read and verify their evidence READMEs.
Finish contract
- If a 256-GiB-class host with at least 224 GiB runtime-accessible memory is unavailable, write
evidence/DGR-018/BLOCKED.mdwith exact preflight output; do not substitute a smaller model. - Preserve real failures and blockers; never fabricate output.
- Emit
<promise>COMPLETE</promise>only after the signed oracle evidence exists.