popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: cryptographically bind DGR-001 evidence

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-13 19:38:14 +03:00
parent 9e67b829e3
commit b1c9deeb01
11 changed files with 1349 additions and 903 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
.scratch/distributed-gguf-runtime/evidence/DGR-001/contract-evaluation.json
View File

@@ -17,22 +17,22 @@
"lane": "quality",
"measurements": {
"aggregate_concurrency": 4,
"aggregate_throughput_speedup": 4.4882,
"aggregate_throughput_speedup": 4.7873,
"artifact_size_ratio": 0.9946,
"artifact_size_win": false,
"compared_prompts": 3,
"decode_speedup": 1.9064,
"decode_speedup": 2.4173,
"exact_match_rate": 0.3333,
"expected_prompts": 3,
"failure_rate": 0.0,
"mean_similarity": 0.9471,
"resident_memory_ratio": 0.5722,
"ttft_ratio": 1.1729
"resident_memory_ratio": 0.5721,
"ttft_ratio": 0.3767
},
"quality_pass": false,
"reasons": [
"single-request decode 1.91x reference (>= 1.25x) at TTFT ratio 1.17",
"aggregate throughput at concurrency 4 is 4.49x reference (>= 1.25x)",
"single-request decode 2.42x reference (>= 1.25x) at TTFT ratio 0.38",
"aggregate throughput at concurrency 4 is 4.79x reference (>= 1.25x)",
"peak resident memory is 0.57x reference (<= 0.75x)",
"quality lane exact-match 0.33 / similarity 0.947 versus the reference (fail)"
],
@@ -47,18 +47,18 @@
"lane": "performance-fit",
"measurements": {
"aggregate_concurrency": 4,
"aggregate_throughput_speedup": 4.3826,
"aggregate_throughput_speedup": 4.2048,
"artifact_size_ratio": 0.398,
"artifact_size_win": true,
"decode_speedup": 3.6869,
"decode_speedup": 5.0967,
"failure_rate": 0.0,
"resident_memory_ratio": 0.2793,
"ttft_ratio": 0.6367
"resident_memory_ratio": 0.2792,
"ttft_ratio": 0.5395
},
"quality_pass": null,
"reasons": [
"single-request decode 3.69x reference (>= 1.25x) at TTFT ratio 0.64",
"aggregate throughput at concurrency 4 is 4.38x reference (>= 1.25x)",
"single-request decode 5.10x reference (>= 1.25x) at TTFT ratio 0.54",
"aggregate throughput at concurrency 4 is 4.20x reference (>= 1.25x)",
"peak resident memory is 0.28x reference (<= 0.75x)"
],
"recipe_id": "llama-cpp-quantized-performance-fit",