{ "schema": 1, "recordedAt": "2026-11-02T18:43:08.188400+00:00", "status": "macOS spike qualified; completion API only", "source": { "repository": "microsoft/phi-2", "revision": "9a5117d15e407c48fa40f8adbac1244abae52d6f", "license": "mit" }, "modelSHA256": "8b2a3f6388406f183163440449aced556008f05e6b7a0308b1d423bc2ce79085", "architectureAdditions": [ "partial rotary dimensions and shared prefix rotation", "optional output-head bias", "parallel residual family block", "noninterleaved strided KV updates and growth" ], "arithmeticPolicy": { "residuals": "float32", "projections": "float32", "normalization": "float32", "weights": "float16", "cache": "float16", "logits": "float16", "rotaryFrequencyInitialization": "float32" }, "swiftRegression": { "reportedTests": 714, "testExecutables": 18, "configuration": "Release, arm64-apple-macosx27.0", "passed": true, "logSHA256": "e5709cb19629857c6858980ecfff094986687a5dba4eeda21ac06dcdd31ad04a" }, "pythonRegression": { "testMethods": 10, "passed": true, "families": [ "qwen3", "olmo2", "gpt2", "phi" ] }, "coreAICPU": { "passed": true, "minimumCosine": 0.99298, "exactArgmax": true, "lostCacheRows": 0 }, "cases": { "short": { "promptTokens": 7, "eagerPortVsReference": { "running": { "minCosine": 0.99999994, "maxAbs": 0.003997, "argmaxEqualRows": 64, "rows": 64, "withinFloat32Tolerance": true }, "bucketed": { "minCosine": 0.99999996, "maxAbs": 0.003875, "argmaxEqualRows": 64, "rows": 64, "withinFloat32Tolerance": true } }, "nativeMinimumCosine": 0.9984728627398196, "nativeForcedRows": 64, "nativeArgmaxMismatches": 0, "nativeGreedyIdentical": true, "cacheGrowths": 0, "allocatedCapacity": 256, "passed": true }, "long": { "promptTokens": 280, "eagerPortVsReference": { "running": { "minCosine": 0.99999995, "maxAbs": 0.008103, "argmaxEqualRows": 64, "rows": 64, "withinFloat32Tolerance": true }, "bucketed": { "minCosine": 0.99999995, "maxAbs": 0.008518, "argmaxEqualRows": 64, "rows": 64, "withinFloat32Tolerance": true } }, "nativeMinimumCosine": 0.9991725048462431, "nativeForcedRows": 64, "nativeArgmaxMismatches": 0, "nativeGreedyIdentical": true, "cacheGrowths": 0, "allocatedCapacity": 512, "passed": true }, "growth": { "promptTokens": 224, "eagerPortVsReference": { "running": { "minCosine": 0.99999995, "maxAbs": 0.005407, "argmaxEqualRows": 64, "rows": 64, "withinFloat32Tolerance": true }, "bucketed": { "minCosine": 0.99999996, "maxAbs": 0.006926, "argmaxEqualRows": 64, "rows": 64, "withinFloat32Tolerance": true } }, "nativeMinimumCosine": 0.9990648427426364, "nativeForcedRows": 64, "nativeArgmaxMismatches": 0, "nativeGreedyIdentical": true, "cacheGrowths": 3, "allocatedCapacity": 512, "passed": true } }, "float32Tolerance": { "phiAtol": 0.01, "rtol": 0, "minimumCosine": 0.999999, "argmax": "all rows equal", "upstreamOnlyMaxAbs": 0.008141040802001953 }, "contiguousCacheNativeRegression": { "family": "gpt2", "passed": true }, "localBundle": ".local/phi2-qualified/bundle", "limitations": [ "no iOS qualification", "base completion model; no chat template", "no hosted bundle", "interleaved KV storage remains unsupported" ] }