Files
OBLITERATUS/tests/fixtures/quant_dequant_provenance.json
T

22 lines
868 B
JSON

{
"schema_version": 1,
"origin": "synthetic-runtime-generated",
"external_data": false,
"contract_sources": [
"https://docs.vllm.ai/projects/llm-compressor/en/stable/guides/entrypoints/convert/",
"https://github.com/huggingface/transformers/blob/main/docs/source/en/quantization/compressed_tensors.md"
],
"generator": "tests/test_quant_dequant.py",
"torch_manual_seeds": [0, 1, 2, 3, 4, 5, 6, 7, 8],
"formats": {
"fp8": "IEEE-like E4M3 values generated by torch.float8_e4m3fn",
"nvfp4": "E2M1 values generated from OBLITERATUS's explicit 16-value test oracle"
},
"oracles": {
"fp8_relative_l2_max": 0.05,
"nvfp4_relative_l2_max": 0.15,
"nvfp4_cosine_min": 0.995
},
"reproducibility": "Fixtures are regenerated deterministically during each test run; no model weights, datasets, or network resources are consumed."
}