{
  "concurrency_sweep": {
    "corruption_free": true,
    "reference_outputs": {
      "s0": [
        27,
        8,
        27,
        8,
        27,
        8,
        1,
        1
      ],
      "s1": [
        26,
        39,
        39,
        39,
        39,
        3,
        39,
        39
      ],
      "s2": [
        12,
        12,
        12,
        12,
        12,
        12,
        30,
        12
      ],
      "s3": [
        29,
        41,
        42,
        47,
        47,
        42,
        47,
        42
      ],
      "s4": [
        23,
        11,
        44,
        29,
        29,
        29,
        41,
        29
      ],
      "s5": [
        35,
        11,
        0,
        1,
        11,
        0,
        11,
        15
      ],
      "s6": [
        39,
        39,
        28,
        39,
        39,
        39,
        28,
        28
      ],
      "s7": [
        39,
        39,
        39,
        39,
        39,
        39,
        8,
        47
      ]
    },
    "results": [
      {
        "avg_batch_occupancy": 1.0,
        "cache_misses": 0,
        "concurrency": 1,
        "decode_batches": 56,
        "decode_tokens": 56,
        "max_batch_occupancy": 1,
        "peak_kv_bytes": 15360,
        "prefill_tokens": 32,
        "rejected_admissions": 0,
        "ticks": 64,
        "tokens_per_tick": 1.375
      },
      {
        "avg_batch_occupancy": 1.75,
        "cache_misses": 0,
        "concurrency": 2,
        "decode_batches": 32,
        "decode_tokens": 56,
        "max_batch_occupancy": 2,
        "peak_kv_bytes": 29184,
        "prefill_tokens": 32,
        "rejected_admissions": 0,
        "ticks": 33,
        "tokens_per_tick": 2.6667
      },
      {
        "avg_batch_occupancy": 3.1111,
        "cache_misses": 0,
        "concurrency": 4,
        "decode_batches": 18,
        "decode_tokens": 56,
        "max_batch_occupancy": 4,
        "peak_kv_bytes": 52224,
        "prefill_tokens": 32,
        "rejected_admissions": 0,
        "ticks": 19,
        "tokens_per_tick": 4.6316
      },
      {
        "avg_batch_occupancy": 4.0,
        "cache_misses": 0,
        "concurrency": 8,
        "decode_batches": 14,
        "decode_tokens": 56,
        "max_batch_occupancy": 7,
        "peak_kv_bytes": 75264,
        "prefill_tokens": 32,
        "rejected_admissions": 0,
        "ticks": 15,
        "tokens_per_tick": 5.8667
      }
    ],
    "saturation_concurrency": 8,
    "schema_version": 1
  },
  "evidence_kind": "synthetic-unit",
  "mid_run_telemetry_concurrency_4": {
    "active_sessions": 4,
    "batch_occupancy_avg": 4.0,
    "batch_occupancy_last": 4,
    "batch_occupancy_max": 4,
    "completed_sessions": 0,
    "decode_tokens_per_sec": 1637.355,
    "decode_tokens_total": 20,
    "kv_budget_bytes": 67108864,
    "kv_pressure": 0.0008,
    "kv_total_bytes": 55296,
    "prefill_tokens_per_sec": 1309.884,
    "prefill_tokens_total": 16,
    "queue_depth": 4,
    "rejected_admissions_total": 0,
    "rejected_by_reason": {},
    "scratch_budget_bytes": 4,
    "scratch_pressure": 1.0,
    "scratch_used_bytes": 4,
    "ticks": 6,
    "weight_bytes": 0
  },
  "model": {
    "hidden": 32,
    "n_heads": 4,
    "n_layers": 6,
    "reference": "pure-numpy KV-cached dense-Llama (tests/test_hot_kv_state)",
    "vocab": 48
  },
  "schema_version": 1,
  "workload": {
    "max_new_tokens": 8,
    "prompt_len": 4,
    "sessions": 8
  }
}