{ "status": "pass", "profile": "mlp-only", "comparison": "BF16 weights vs block-FP8 weights dequantized to BF16", "input_distribution": "fixed-seed unit-normal BF16 vectors (RMSNorm-like)", "samples_per_mlp": 64, "samples_per_attention_output_projection": 128, "mlp_aggregate": { "rmse": 51.15606406613011, "relative_rmse": 0.028808014285076088, "cosine_similarity": 0.999586214895275, "maximum_absolute_error": 1024.0 }, "attention_output_projection_aggregate": { "rmse": 0.0, "relative_rmse": 0.0, "cosine_similarity": 1.0, "maximum_absolute_error": 0.0 }, "gates": { "mlp_relative_rmse_max": 0.1, "mlp_cosine_similarity_min": 0.995, "attention_relative_rmse_max": 0.05, "attention_cosine_similarity_min": 0.998 }, "per_layer_mlp": [ { "layer": 0, "rmse": 46.944710713054484, "relative_rmse": 0.02199275336409562, "cosine_similarity": 0.9997595575772288, "maximum_absolute_error": 1024.0, "squared_error": 722143105.4933598, "reference_energy": 1493014623467.2358, "dot": 1489775007178.6418, "candidate_energy": 1487257533995.5679, "elements": 327680 }, { "layer": 1, "rmse": 51.91130504990165, "relative_rmse": 0.031573682259121584, "cosine_similarity": 0.9995025435310865, "maximum_absolute_error": 1024.0, "squared_error": 883026687.421299, "reference_energy": 885774882473.856, "dot": 883571172877.6316, "candidate_energy": 882250489968.8706, "elements": 327680 }, { "layer": 2, "rmse": 53.50805681930253, "relative_rmse": 0.03490318748371408, "cosine_similarity": 0.9993913110064463, "maximum_absolute_error": 512.0, "squared_error": 938184587.5352235, "reference_energy": 770119488860.0505, "dot": 768330396334.169, "candidate_energy": 767479488395.8666, "elements": 327680 }, { "layer": 3, "rmse": 51.742237285112125, "relative_rmse": 0.038977179685573425, "cosine_similarity": 0.9992402571060341, "maximum_absolute_error": 384.0, "squared_error": 877284268.2020159, "reference_energy": 577456825572.1453, "dot": 576257438543.1458, "candidate_energy": 575935335782.396, "elements": 327680 }, { "layer": 4, "rmse": 51.43689078790791, "relative_rmse": 0.024536587190349065, "cosine_similarity": 0.9997013312358347, "maximum_absolute_error": 1024.0, "squared_error": 866960583.5332537, "reference_energy": 1440028343049.15, "dot": 1436015671674.3086, "candidate_energy": 1432869960883.038, "elements": 327680 } ], "per_layer_attention_output_projection": [ { "layer": 0, "rmse": 0.0, "relative_rmse": 0.0, "cosine_similarity": 1.0, "maximum_absolute_error": 0.0, "squared_error": 0.0, "reference_energy": 33139259.3109601, "dot": 33139259.3109601, "candidate_energy": 33139259.3109601, "elements": 655360 }, { "layer": 1, "rmse": 0.0, "relative_rmse": 0.0, "cosine_similarity": 1.0, "maximum_absolute_error": 0.0, "squared_error": 0.0, "reference_energy": 41008694.364316456, "dot": 41008694.364316456, "candidate_energy": 41008694.364316456, "elements": 655360 }, { "layer": 2, "rmse": 0.0, "relative_rmse": 0.0, "cosine_similarity": 1.0, "maximum_absolute_error": 0.0, "squared_error": 0.0, "reference_energy": 47956004.669400826, "dot": 47956004.669400826, "candidate_energy": 47956004.669400826, "elements": 655360 }, { "layer": 3, "rmse": 0.0, "relative_rmse": 0.0, "cosine_similarity": 1.0, "maximum_absolute_error": 0.0, "squared_error": 0.0, "reference_energy": 54665058.895079024, "dot": 54665058.895079024, "candidate_energy": 54665058.895079024, "elements": 655360 }, { "layer": 4, "rmse": 0.0, "relative_rmse": 0.0, "cosine_similarity": 1.0, "maximum_absolute_error": 0.0, "squared_error": 0.0, "reference_energy": 76522649.49797027, "dot": 76522649.49797027, "candidate_energy": 76522649.49797027, "elements": 655360 } ], "limitation": "This validates selected sublayer arithmetic, not native W8A8 kernels or end-to-end DFlash2 acceptance. The current DFlash2 vLLM implementation is an unmerged experimental branch.", "elapsed_seconds": 1.1974219349795021 }