37 lines
1.7 KiB
JSON
37 lines
1.7 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"contract_version": 1,
|
|
"locked_at": "2026-07-13T00:00:00Z",
|
|
"locked_by": "DGR-001",
|
|
"plan_id": "dgr-001-controlled-whole-model-baseline-v1",
|
|
"thresholds": {
|
|
"min_decode_speedup": 1.25,
|
|
"max_ttft_ratio": 1.25,
|
|
"min_aggregate_throughput_speedup": 1.25,
|
|
"max_resident_memory_ratio": 0.75,
|
|
"max_artifact_size_ratio": 0.6,
|
|
"min_quality_exact_match_rate": 0.9,
|
|
"min_quality_mean_similarity": 0.97,
|
|
"max_failure_rate": 0.0
|
|
},
|
|
"baseline": {
|
|
"status": "pending-real-evidence",
|
|
"required_evidence_class": "local-real",
|
|
"required_recipes": [
|
|
"transformers-safetensors-reference",
|
|
"llama-cpp-near-lossless-quality",
|
|
"llama-cpp-quantized-performance-fit"
|
|
],
|
|
"required_concurrency_levels": [1, 4],
|
|
"required_controlled_variables": [
|
|
"model architecture",
|
|
"model revision",
|
|
"machine and device",
|
|
"formatted prompts and context lengths",
|
|
"output length and greedy sampling policy"
|
|
]
|
|
},
|
|
"stop_condition": "Stop the native llama.cpp/GGUF track when, on the same machine and device as the Transformers/safetensors reference and under this plan, no performance-fit GGUF recipe delivers either a meaningful speed benefit (at least 25% higher single-request decode tokens/sec without more than 25% worse TTFT, or at least 25% higher aggregate throughput under concurrency) or a meaningful fit benefit (at least 25% lower peak resident memory), or when the near-lossless quality lane fails.",
|
|
"notes": "Quantized performance-fit output drift is reported as advisory only. It is not numerical-equivalence evidence. DGR-014 consumes this immutable v1 contract."
|
|
}
|