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

47
.scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json
View File

@@ -37,8 +37,51 @@
"minimum_prompt_count": 3,
"minimum_repeats": 3,
"minimum_output_tokens": 32,
"required_device": "cpu"
"required_device": "cpu",
"required_config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
"required_signer_public_key": "zQ/qRMwF/ydazzaxEI24Xvnrl5bZxzw16JYpP0bfRuI=",
"required_artifact_sha256": {
"transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
"llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
"llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5"
},
"required_recipe_runtime": {
"transformers-safetensors-reference": {
"runtime": "transformers-5.13.0",
"weight_format": "safetensors",
"weight_quantization": "bfloat16",
"device": "cpu"
},
"llama-cpp-near-lossless-quality": {
"runtime": "llama.cpp-9991-e920c523",
"weight_format": "gguf",
"weight_quantization": "bfloat16",
"device": "cpu"
},
"llama-cpp-quantized-performance-fit": {
"runtime": "llama.cpp-9991-e920c523",
"weight_format": "gguf",
"weight_quantization": "Q4_K_M",
"device": "cpu"
}
},
"required_backend_detail": {
"transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16",
"llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
"llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0"
},
"required_host_identity": {
"python": "3.12.13",
"torch_version": "2.10.0+rocm7.13.0a20260513",
"transformers_version": "5.13.0",
"llama_server_identities": {
"/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
"sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
"version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
}
}
}
},
"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 (>=25% higher single-request decode tokens/sec without a >25% worse TTFT, or >=25% higher aggregate throughput under concurrency) or a meaningful fit benefit (>=25% lower peak resident memory), or when the near-lossless quality lane fails, which indicates a broken runtime rather than a quantization trade-off.",
"notes": "Quantized performance-fit output drift is reported as advisory only. It is not numerical-equivalence evidence. DGR-014 consumes this immutable v1 contract."
"notes": "Quantized performance-fit output drift is reported as advisory only. It is not numerical-equivalence evidence. DGR-014 consumes this immutable v1 contract. Non-synthetic evidence must be Ed25519-signed by the pinned key and match the exact locked config, artifacts, runtimes, backends, and host runtime identity."
}