{ "schema": 1, "updated_utc": "2026-10-20T20:43:34.031803+00:00", "source_commit": "f74e2fa6a31cc33ab4ee4ae516641cfe62df3924", "modified_source": true, "passed": false, "release_ready": false, "verdict": "Fresh numerical tests pass; release blocked by the original uncaptured Q5_1 input under the every-failure evidence requirement.", "gates": { "kernels": { "passed": false, "fresh_runs_passed": true, "historical_failure_evidence_complete": false }, "model_agreement": { "passed": true }, "flash_attention": { "passed": true, "targeted_regression_passed": 1, "full_family_passed": 12012, "full_family_failed": 0, "full_family_unsupported": 4017 }, "package": { "passed": true, "binary_relocation_passed": true, "privacy_passed": true, "checksum_verified_before_document_refresh": true }, "docs": { "passed": true, "speed_results": "placeholder requested" } }, "kernels": { "passed": true, "complete_runs": 3, "runs": [ { "exit_code": 0, "counts": { "passed": 9784, "failed": 0, "unsupported": 1793 }, "families": { "MUL_MAT": { "passed": 3918, "failed": 0, "unsupported": 420 }, "MUL_MAT_ID": { "passed": 962, "failed": 0, "unsupported": 14 }, "FLASH_ATTN_EXT": { "passed": 4004, "failed": 0, "unsupported": 1339 }, "SSM_CONV": { "passed": 135, "failed": 0, "unsupported": 0 }, "GATED_DELTA_NET": { "passed": 48, "failed": 0, "unsupported": 0 }, "RMS_NORM": { "passed": 53, "failed": 0, "unsupported": 0 }, "ROPE": { "passed": 450, "failed": 0, "unsupported": 20 }, "SOFT_MAX": { "passed": 214, "failed": 0, "unsupported": 0 } }, "failed_cases": [], "passed": true, "attempt": 4, "stdout_sha256": "8c6fa2b880b8f196626891815d0e56387134c29bef786c9896388e46eddc785f", "stderr_sha256": "f7b016d89dc0f27c6384e483758987c04fc856b6eff33cedd9ef183adf2cdb75", "elapsed_s": 746.3958051204681, "q5_1_cases": 59, "q5_1_mul_mat_cases": 56 }, { "exit_code": 0, "counts": { "passed": 9784, "failed": 0, "unsupported": 1793 }, "families": { "MUL_MAT": { "passed": 3918, "failed": 0, "unsupported": 420 }, "MUL_MAT_ID": { "passed": 962, "failed": 0, "unsupported": 14 }, "FLASH_ATTN_EXT": { "passed": 4004, "failed": 0, "unsupported": 1339 }, "SSM_CONV": { "passed": 135, "failed": 0, "unsupported": 0 }, "GATED_DELTA_NET": { "passed": 48, "failed": 0, "unsupported": 0 }, "RMS_NORM": { "passed": 53, "failed": 0, "unsupported": 0 }, "ROPE": { "passed": 450, "failed": 0, "unsupported": 20 }, "SOFT_MAX": { "passed": 214, "failed": 0, "unsupported": 0 } }, "failed_cases": [], "passed": true, "attempt": 5, "stdout_sha256": "8c6fa2b880b8f196626891815d0e56387134c29bef786c9896388e46eddc785f", "stderr_sha256": "f7b016d89dc0f27c6384e483758987c04fc856b6eff33cedd9ef183adf2cdb75", "elapsed_s": 704.5498714447021, "q5_1_cases": 59, "q5_1_mul_mat_cases": 56 }, { "exit_code": 0, "counts": { "passed": 9784, "failed": 0, "unsupported": 1793 }, "families": { "MUL_MAT": { "passed": 3918, "failed": 0, "unsupported": 420 }, "MUL_MAT_ID": { "passed": 962, "failed": 0, "unsupported": 14 }, "FLASH_ATTN_EXT": { "passed": 4004, "failed": 0, "unsupported": 1339 }, "SSM_CONV": { "passed": 135, "failed": 0, "unsupported": 0 }, "GATED_DELTA_NET": { "passed": 48, "failed": 0, "unsupported": 0 }, "RMS_NORM": { "passed": 53, "failed": 0, "unsupported": 0 }, "ROPE": { "passed": 450, "failed": 0, "unsupported": 20 }, "SOFT_MAX": { "passed": 214, "failed": 0, "unsupported": 0 } }, "failed_cases": [], "passed": true, "attempt": 7, "stdout_sha256": "8c6fa2b880b8f196626891815d0e56387134c29bef786c9896388e46eddc785f", "stderr_sha256": "f7b016d89dc0f27c6384e483758987c04fc856b6eff33cedd9ef183adf2cdb75", "elapsed_s": 769.3762726783752, "q5_1_cases": 59, "q5_1_mul_mat_cases": 56 } ], "counts": { "passed": 29352, "failed": 0, "unsupported": 5379 }, "families": { "MUL_MAT": { "passed": 11754, "failed": 0, "unsupported": 1260 }, "MUL_MAT_ID": { "passed": 2886, "failed": 0, "unsupported": 42 }, "FLASH_ATTN_EXT": { "passed": 12012, "failed": 0, "unsupported": 4017 }, "SSM_CONV": { "passed": 405, "failed": 0, "unsupported": 0 }, "GATED_DELTA_NET": { "passed": 144, "failed": 0, "unsupported": 0 }, "RMS_NORM": { "passed": 159, "failed": 0, "unsupported": 0 }, "ROPE": { "passed": 1350, "failed": 0, "unsupported": 60 }, "SOFT_MAX": { "passed": 642, "failed": 0, "unsupported": 0 } }, "q5_1_cases": 177, "excluded_attempts": { "1": "owner interruption", "2": "owner interruption", "3": "owner interruption", "6": "lease deferral; test never launched" }, "q5_1_mul_mat_cases": 168, "classification_rule": "MUL_MAT_ID and MUL_MAT_ID_* classified before MUL_MAT*; same corrected rule as initial comparison." }, "model_agreement": { "passed": true, "scored_positions": 1020, "context": 512, "chunks": 4, "mean_kld": 0.000597, "p99_kld": 0.0162, "maximum_kld": 0.040878, "same_top_percent": 99.51, "cpu_ppl": 1.155534, "gpu_ppl": 1.154694, "ppl_ratio": 0.999273, "ppl_delta": -0.00084, "corpus_sha256": "68c3808a113f74773f6c3c278173171358f2402d4e38e116ae6a03aca0263055", "reference_log_probs_sha256": "4e71a366b8cc432cdf6b9c8c2add9cd8f69cd28b4fc6652ee72eab61acbfa223", "same_top_count": 1015, "thresholds": { "mean_kld_max": 0.001, "same_top_percent_min": 99, "absolute_ppl_change_percent_max": 0.5 }, "base_format_note": "Upstream --kl-divergence-base stores scaled uint16 log probabilities; reported KLD is the upstream estimate, including its p > exp(-16) cutoff.", "cpu_only_verified": true, "gpu_offload_layers": [ 41, 41 ], "flash_attention": "enabled", "ppl_relative_change_percent": -0.07269366370872277, "model": { "filename": "MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf", "sha256": "9ecf91e814d7e9adc64325b1b65f8628a9b1bb8da4f61a92869ca7489bfd888e", "size_bytes": 21166255008 } }, "historical_q5_1_failure": { "op": "MUL_MAT", "type_a": "q5_1", "shape": { "m": 16, "n": 1, "k": 256 }, "nmse": 0.00074011, "threshold": 0.0005, "threshold_multiple": 1.48022, "input_captured": false, "exact_cpu_replay_available": false, "conditioning_proven": false, "initial_supported_mul_mat_cases": 3918, "initial_plus_fresh_mul_mat_cases": 15672, "initial_plus_fresh_failures": 1, "initial_plus_fresh_observed_failure_fraction": 6.380806533945891e-05, "blocked_requirement": "Every failure must retain its input and be replayed on CPU with evidence establishing input conditioning." }, "additional_reported_evidence": { "independently_rerun_in_this_validation": false, "v100_q5_1": { "runs": 20, "passed": 1120, "failed": 0 }, "sm86_q5_1": { "runs": 5, "passed": 280, "failed": 0 }, "not_in_fresh_gate_counts": true }, "greedy": { "is_gate": false, "first_divergence_1_based": { "reasoning": 26, "prose": 12, "code": null }, "tokens_per_prompt": 64 }, "instrumentation": { "original_test_source_sha256": "9acaf591366b892274dc5167308c2d9f6d82f257d1e9b9d9225be79d3e944b05", "diagnostic_source_sha256": "3bbe160c550ee73193ec1d945c3154b9f10125c01f9de82c269a9c7c09f73a40", "diagnostic_helper_sha256": "467e6d876f89fa203b6c185d81428bbb9470459c8193cd3306f5c52aa6ee1950", "diagnostic_binary_sha256": "ff53ce0b103513584a3345a7a248fa9634c157d0a04fe58ad81d1d1385bbd7cf", "production_unchanged": true, "instrumentation": "Header include, CPU-only replay CLI branch, and capture calls immediately before existing comparison failure prints only", "limitations": "Allocation/backend execution failures before comparison have no pair of outputs to capture. Fused intermediate outputs may not be materialized; the compared root output is valid." }, "relocation": { "files": [ { "file": "libggml-base.so.0.27.0", "build_matches": true, "unpacked_matches": true }, { "file": "libggml-cpu.so.0.27.0", "build_matches": true, "unpacked_matches": true }, { "file": "libggml-cuda.so.0.27.0", "build_matches": true, "unpacked_matches": true }, { "file": "libggml.so.0.27.0", "build_matches": true, "unpacked_matches": true }, { "file": "libllama-bench-impl.so", "build_matches": true, "unpacked_matches": true }, { "file": "libllama-cli-impl.so", "build_matches": true, "unpacked_matches": true }, { "file": "libllama-common.so.0.7.0", "build_matches": true, "unpacked_matches": true }, { "file": "libllama-perplexity-impl.so", "build_matches": true, "unpacked_matches": true }, { "file": "libllama-quantize-impl.so", "build_matches": true, "unpacked_matches": true }, { "file": "libllama-server-impl.so", "build_matches": true, "unpacked_matches": true }, { "file": "libllama.so.0.7.0", "build_matches": true, "unpacked_matches": true }, { "file": "libmtmd.so.0.7.0", "build_matches": true, "unpacked_matches": true }, { "file": "llama-bench", "build_matches": true, "unpacked_matches": true }, { "file": "llama-cli", "build_matches": true, "unpacked_matches": true }, { "file": "llama-perplexity", "build_matches": true, "unpacked_matches": true }, { "file": "llama-quantize", "build_matches": true, "unpacked_matches": true }, { "file": "llama-server", "build_matches": true, "unpacked_matches": true }, { "file": "test-backend-ops", "build_matches": true, "unpacked_matches": true } ], "tools": [ { "tool": "llama-server", "probe": "--version", "exit_code": 0, "all_dependencies_found": true, "no_build_dependencies": true }, { "tool": "llama-cli", "probe": "--version", "exit_code": 0, "all_dependencies_found": true, "no_build_dependencies": true }, { "tool": "llama-bench", "probe": "--version", "exit_code": 0, "all_dependencies_found": true, "no_build_dependencies": true }, { "tool": "llama-perplexity", "probe": "--version", "exit_code": 0, "all_dependencies_found": true, "no_build_dependencies": true }, { "tool": "llama-quantize", "probe": "--help", "exit_code": 1, "all_dependencies_found": true, "no_build_dependencies": true }, { "tool": "test-backend-ops", "probe": "--help", "exit_code": 1, "all_dependencies_found": true, "no_build_dependencies": true } ], "environment": { "LD_LIBRARY_PATH": "unset", "CUDA_VISIBLE_DEVICES": "empty", "PATH": "/usr/bin:/bin" }, "unpacked_folder_preexisting": true, "runtime_only_limitation": "Host has a CUDA toolkit installed; probes and ELF dependencies use only runtime libraries, without nvcc in PATH. This is not an isolated runtime-only OS image.", "passed": true, "supported_version_probes_passed": 4, "usage_probes_passed": 2 }, "binary_sha256": { "libggml-base.so.0.27.0": "7dec032a7496b1ade3f9db26585c3eff5d7fe0940c694179e43d087edc5aa641", "libggml-cpu.so.0.27.0": "9328d2600994cc61b76226b1865afc3f2e71945b7f2793e473fc84796df6ff36", "libggml-cuda.so.0.27.0": "97acd2d0b82674e731605705a7d4c826604840bbcfc4eea7987286cdc9bc5a79", "libggml.so.0.27.0": "9f39ebbcae29ee028ab45fec86b0f312dc6e3a0ec4db419c1deb86347c18d621", "libllama-bench-impl.so": "084d5060baae43d8fae2a3de35d743183f124eace7e264d2657ea6c5547e19c0", "libllama-cli-impl.so": "9246772a78adc8581adbed42b16bdc17ddc891479647dea73cad5906bfc16f52", "libllama-common.so.0.7.0": "fd83ff307e92e64b32aca8799dde1eb4791ccc274e84ca8ae19e6d299533a199", "libllama-perplexity-impl.so": "43170cc0162c08eb09054905476523cdd8292f6b2de959e733ccf01cbe5dce7e", "libllama-quantize-impl.so": "55f2bf9cc8088be6078e90f3c826eac11a1cc89fc5e34821944e9b3f02a1c394", "libllama-server-impl.so": "6b5fbb17ee399774b421c8190c87051e95a54177a5d9370edabd60e9094f43da", "libllama.so.0.7.0": "f02e3993196df4f2c7403d53b3ce3afd6705678a941497c7250ff2d6c316210b", "libmtmd.so.0.7.0": "997927073ce7c6601db58cdc57bfba5891ec6dca63d5a6374a8f87de51b672e1", "llama-bench": "c542ade6b00f3e108efa8312776b17dbca8cceef45590845236328f67fb9ad7c", "llama-cli": "00272bbaf8704619739c2ecbe970eb53a9d2c7544c26c8f41730e0dde0fa4a65", "llama-perplexity": "b42d4afd0013c8d54c80cd84057beea784d094d9710f6fa3e9209fcce1862690", "llama-quantize": "dded52ad19ad77f40fe678ad7b06627fc442cd437e3cd44b8c9f4c34b04115a7", "llama-server": "0015eb3199723cfae5a15ec89bdbccc9fde8bd652c589179d134587804964b98", "test-backend-ops": "bca163572bc5206896c68e2cab98612c97e31445a642aebdfbef8dd01d1685b7" }, "initial_validation_sha256": "49d0be0dd26591fa042c54e07c62b642fbd37dedfeb358001238f58486dd465b", "publication": "none", "license": "MIT; preserve LICENSE and THIRD-PARTY-NOTICES" }