{
  "runtime_version": "10",
  "orbitquant_version": "0.9.7",
  "orbitquant_commit": "5c624b088cd9378a135a5fe44bc4ea71f5d288da",
  "native_kernel_version": "1.0.4",
  "native_wheel_sha256": "13aa3db06ae9e90d9c9ef90ed3ead367743bd8582dc8731c82c5e35d47b5ae16",
  "fast_kernel_source_commit": "7795243b1b9066b5463b4625f16e36e6e4e6682f",
  "fast_kernel_build_note": "kernel-builder generated files made the build namespace dirty; source content and exact binary are included and hashed",
  "experimental_archive": {
    "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
    "revision": "1edba493f504208488fd7d98fe1312ff52b02365",
    "path": "profile-round2"
  },
  "weight_generation_source_lock": "../source-lock.json",
  "orbitquant_wheel_sha256": "7f612c79441b14529c9a7d0f35cb22cc871e3a9b33d24f9a19352cb3e2ff9bdb",
  "rms_quant_kernel": {
    "source_commit": "92dbd686220262d8d24b09c27a6d6703e19f9465",
    "module": "_yue2_qkv_fused_cuda_cf0db58",
    "binary_sha256": "1ca79342c379a231d86fa5c8e94e45134c3624d7b85ca5e55997004ec69ff542",
    "source_path": "kernel-source/rms-quant",
    "arithmetic": "FP32 x*gamma; RMS scalar folded into activation norm; original epsilon rescaled before flooring",
    "scope": "explicit fuse_rms_quant flag; AR decode only; eager prefill and NAR retain existing paths"
  },
  "round5_archive": {
    "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
    "revision": "ab852c01399038009c9db216f16cd22cd4390f82",
    "path": "profile-round5"
  },
  "captured_sampling": {
    "scope": "request-owned combined decode/CFG/sampling graph for ABC and semantic; fast/memory; positive temperature and CUDA graph decode only",
    "rng": "caller-owned generator registered with CUDA graph; capture/warmup restore advanced state; no module cache",
    "opt_out": "--no-captured-sampling / capture_sampling=False",
    "research_archive": {
      "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
      "revision": "acfb177adfb11dceb89fb8cc6b0382554c1c4e19",
      "path": "profile-round6/captured-sampler-interleaved"
    },
    "abc_research_archive": {
      "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
      "revision": "b8892ba75691c8ab0427ebd96838bf78bec62a91",
      "path": "profile-round7/captured-abc-interleaved"
    },
    "history": "device ring and counter; no per-token host history upload",
    "first_token": "separate prefill sampler; combined graph starts with the second token",
    "research_archive_v6": {
      "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
      "revision": "bdae011fa163b52e062f6f0855cddb7d4d1f73f0",
      "path": "profile-round8"
    }
  },
  "paired_row_decode": {
    "rows": "2..8",
    "minimum_output_features": 2048,
    "input_features": "1024..16384",
    "weight_layout": "row-major",
    "archive_revision": "7344aedfa6c322229259796b3eab0941046f655e",
    "archive_path": "profile-round9/native-evidence",
    "native_build_workflow": 34665811056
  },
  "int8_kv_cache": {
    "source_commit": "fcfedee4713ca864d55641cf4902b4eeef725de3",
    "binary_sha256": "a7d62fa5d79d8f0e2d4bb6bd0676b1b59a8676c7fcb615785eadc230e1f88022",
    "source_path": "kernel-source/int8-kv",
    "scope": "optional AR decode cache; BF16 prefill; fast/memory with RMS activation fusion",
    "format": "symmetric signed INT8 per token/head, FP32 scales",
    "default": "bf16",
    "research_revision": "933fbe9dcc2c6eff697504593d0f5e93e2fff229",
    "profile_revision": "7f98a339b66c4c4cef76277f38c285c39027dca8"
  },
  "register_codebook_decode": {
    "native_binary_sha256": "6fb8e94e30e2c9982da5e3e56c04dabed946fe9dc8ad1785c11cc3cf200217b4",
    "source_path": "kernel-source/orbitquant-native",
    "scope": "SM120 only; row-major M1..8, N>=2048, K1024..16384; arbitrary signed INT8 codebooks; paired-row reuse for M>=2",
    "native_build_workflow": 34674570012,
    "python_publish_workflow": 34675461162,
    "release_evidence": {
      "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
      "revision": "a88ed5684e6b7b3148b204d38052becb3d3a8ae8",
      "path": "profile-round12/published-release"
    }
  },
  "int8_attention": {
    "default": "ordered",
    "layouts": {
      "ordered": {
        "source_commit": "193a8d7ad6951dc237435e988986e044bacfe7a9",
        "binary_sha256": "071c866680bb24506680a5d8b2b46c04f60e725ccf9ea6604e4e18973bca4385",
        "source_path": "kernel-source/int8-ordered"
      },
      "subwarp": {
        "source_commit": "4d213ef482b4fbc2733a6e071bf9d5f07ebfa58b",
        "binary_sha256": "d12f0566a396a422eaa35515678fc142ba11b4338aef23c00adf9d095c823778",
        "source_path": "kernel-source/int8-subwarp"
      }
    },
    "reference": "int8_kv_cache",
    "scope": "AR decode only; request GraphAR owns layout; BF16 prefill and cache format unchanged",
    "approximate_research": {
      "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
      "revision": "f4fc2828b6566f464393de29794f56fb1d68044e",
      "path": "profile-round14/subwarp-attention"
    },
    "ordered_research": {
      "repo": "WaveCut/YuE2-3B-OrbitQuant-lab-private",
      "revision": "29502653219877cd2ab8d25466d9b2f39955ceb0",
      "path": "profile-round14/ordered-attention"
    }
  }
}