{
  "method": "indexcache",
  "num_tensors": 5336,
  "num_indexer_tensors": 45,
  "assignments": [
    {
      "layer": 0,
      "role": "group_leader",
      "leader": 0,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 1,
      "role": "shared",
      "leader": 0,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 2,
      "role": "shared",
      "leader": 0,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 3,
      "role": "group_leader",
      "leader": 3,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 4,
      "role": "shared",
      "leader": 3,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 5,
      "role": "shared",
      "leader": 3,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 6,
      "role": "group_leader",
      "leader": 6,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 7,
      "role": "shared",
      "leader": 6,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 8,
      "role": "shared",
      "leader": 6,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 9,
      "role": "group_leader",
      "leader": 9,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 10,
      "role": "shared",
      "leader": 9,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 11,
      "role": "shared",
      "leader": 9,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 12,
      "role": "group_leader",
      "leader": 12,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 13,
      "role": "shared",
      "leader": 12,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 14,
      "role": "shared",
      "leader": 12,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 15,
      "role": "group_leader",
      "leader": 15,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 16,
      "role": "shared",
      "leader": 15,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 17,
      "role": "shared",
      "leader": 15,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 18,
      "role": "group_leader",
      "leader": 18,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 19,
      "role": "shared",
      "leader": 18,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 20,
      "role": "shared",
      "leader": 18,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 21,
      "role": "group_leader",
      "leader": 21,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 22,
      "role": "shared",
      "leader": 21,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 23,
      "role": "shared",
      "leader": 21,
      "offset": 2,
      "group_size": 3
    },
    {
      "layer": 24,
      "role": "group_leader",
      "leader": 24,
      "offset": 0,
      "group_size": 3
    },
    {
      "layer": 25,
      "role": "shared",
      "leader": 24,
      "offset": 1,
      "group_size": 3
    },
    {
      "layer": 26,
      "role": "shared",
      "leader": 24,
      "offset": 2,
      "group_size": 3
    }
  ],
  "all_tensor_shapes_match": true,
  "loading_info": {
    "missing_keys": [],
    "unexpected_keys": [],
    "mismatched_keys": [],
    "error_msgs": []
  },
  "device": "cuda:6",
  "decoder_cpu_offload": true,
  "cache_last_logit_max_abs_diff": 0.1875,
  "cache_last_logit_mean_abs_diff": 0.028124965727329254,
  "generation": "The capital of France is Paris, and the official language is French",
  "sparse_forward_length": 2057,
  "sparse_topk": 2048,
  "runtime_sha256": "712e109ef9d472dc4416def5601296c4f0bf6420f0dd8f7eacf634e6f2825460",
  "seconds": 213.86,
  "unit_tests_passed": 20,
  "unit_subtests_passed": 4,
  "all_exported_tensors_finite": true,
  "safetensors_index_consistent": true,
  "checkpoint_iteration": 1250,
  "validation_note": "GPU inference used decoder CPU offload because shared GPUs lacked free memory for all weights. Cache logit max-absolute BF16 tolerance: 0.5."
}