Files
neuron-tai/.scratch/distributed-gguf-runtime/evidence/DGR-001/quality-parity-diagnosis.json
2026-07-13 21:24:43 +03:00

48 lines
2.7 KiB
JSON

{
"conclusion": {
"conversion_corruption_observed_in_rocm_sample": false,
"cpu_bf16_divergence_explained": false,
"recommended_v2_design": "Predeclare a float32 quality oracle separately from the BF16 performance reference, with a larger prompt corpus and immutable thresholds.",
"scope": "The ROCm diagnostic establishes only that the same BF16 GGUF artifact matched the float32 oracle for three GPU sequences; it does not explain the CPU BF16 divergence or prove global conversion correctness.",
"v1_verdict_changed": false
},
"cpu_v1": {
"candidate": "llama.cpp BF16 GGUF",
"candidate_artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
"config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
"contract_verdict": "stop",
"device": "cpu",
"exact_match_rate": 0.3333,
"mean_similarity": 0.9471,
"plan_id": "dgr-001-controlled-whole-model-baseline-v1",
"plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
"quality_oracle": "Transformers BF16 safetensors",
"report": "results.json",
"report_sha256": "5d99a58806f39821c9206728047b8c5d605027d8a41b88639089b2418da890b5",
"root_cause": "undetermined; no logit-tie claim is acceptance evidence",
"run_id": "e4eedadf-22f6-4907-8990-985456961099"
},
"model_id": "Qwen/Qwen2.5-0.5B-Instruct",
"model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
"rocm_diagnostic": {
"candidate": "llama.cpp BF16 GGUF",
"candidate_artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
"config_sha256": "b0f0c846c818f1307d034cee1f81daa311efc20985c32a4cdbbbd8ffe4153892",
"device": "cuda (ROCm)",
"exact_match_rate": 1.0,
"failures": 0,
"mean_similarity": 1.0,
"measured_backend_detail": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139; threads 16; parallel slots 4; ctx/slot 512; requested gpu layers 99; measured accelerator ROCm0: Radeon 8060S Graphics; measured offload 25/25 layers",
"plan_id": "dgr-001-rocm-gpu-diagnostic-v1",
"plan_sha256": "dae8e40963588f71f5d201fd163d39bd762e392544b5603d483e90d21abee2e8",
"producer": "meshnet_node.recipe_drivers.run_configured_gpu_diagnostic/v1",
"quality_oracle": "Transformers float32 safetensors",
"report": "gpu-diagnostic-results.json",
"report_sha256": "527b33d03627d57d60b30331e6b9119f579a828d6f6acb5c74ca25bab0af5f3d",
"run_id": "31bf44e7-ccd4-4277-84ac-c775dee65411",
"signer_fingerprint": "8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de",
"v1_eligible": false
},
"schema_version": 2
}