{
  "execution_mode": "CPU algorithm with controlled inputs; any latency/capacity coefficients are assumptions",
  "workload": {
    "active_chat_streams": 4,
    "arriving_short_chat_tokens": 256,
    "long_prompt_tokens": 100000,
    "tpot_slo_ms": 50.0
  },
  "monolithic": {
    "mode": "monolithic",
    "token_budget": 2048,
    "tpot_slo_ms": 50.0,
    "total_steps": 61,
    "total_time_ms": 2113.03,
    "max_itl_ms": 1292.21,
    "mean_itl_ms": 34.52,
    "short_chat_ttft_ms": 1268.0,
    "doc_100k_ttft_ms": 1262.91,
    "tpot_slo_met": false,
    "requests": {
      "chat-1": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2113.03,
        "max_itl_ms": 1292.21,
        "mean_itl_ms": 35.81
      },
      "chat-2": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2113.03,
        "max_itl_ms": 1292.21,
        "mean_itl_ms": 35.81
      },
      "chat-3": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2113.03,
        "max_itl_ms": 1292.21,
        "mean_itl_ms": 35.81
      },
      "chat-4": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2113.03,
        "max_itl_ms": 1292.21,
        "mean_itl_ms": 35.81
      },
      "doc-100k": {
        "prompt_tokens": 100000,
        "generated_tokens": 8,
        "ttft_ms": 1262.91,
        "completion_ms": 1377.47,
        "max_itl_ms": 29.3,
        "mean_itl_ms": 16.37
      },
      "chat-5": {
        "prompt_tokens": 256,
        "generated_tokens": 16,
        "ttft_ms": 1268.0,
        "completion_ms": 1490.87,
        "max_itl_ms": 14.21,
        "mean_itl_ms": 14.19
      }
    }
  },
  "chunked_2048": {
    "mode": "chunked",
    "token_budget": 2048,
    "tpot_slo_ms": 50.0,
    "total_steps": 59,
    "total_time_ms": 2034.71,
    "max_itl_ms": 46.63,
    "mean_itl_ms": 34.44,
    "short_chat_ttft_ms": 51.51,
    "doc_100k_ttft_ms": 1907.21,
    "tpot_slo_met": true,
    "requests": {
      "chat-1": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2034.71,
        "max_itl_ms": 46.63,
        "mean_itl_ms": 34.49
      },
      "chat-2": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2034.71,
        "max_itl_ms": 46.63,
        "mean_itl_ms": 34.49
      },
      "chat-3": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2034.71,
        "max_itl_ms": 46.63,
        "mean_itl_ms": 34.49
      },
      "chat-4": {
        "prompt_tokens": 512,
        "generated_tokens": 60,
        "ttft_ms": 0.0,
        "completion_ms": 2034.71,
        "max_itl_ms": 46.63,
        "mean_itl_ms": 34.49
      },
      "doc-100k": {
        "prompt_tokens": 100000,
        "generated_tokens": 8,
        "ttft_ms": 1907.21,
        "completion_ms": 2006.43,
        "max_itl_ms": 14.18,
        "mean_itl_ms": 14.18
      },
      "chat-5": {
        "prompt_tokens": 256,
        "generated_tokens": 16,
        "ttft_ms": 51.51,
        "completion_ms": 565.89,
        "max_itl_ms": 35.96,
        "mean_itl_ms": 33.63
      }
    }
  },
  "stall_reduction_factor": 27.71,
  "budget_sweep": [
    {
      "token_budget": 512,
      "num_prefill_chunks": 198,
      "max_itl_ms": 18.6,
      "mean_itl_ms": 17.99,
      "short_chat_ttft_ms": 24.83,
      "doc_100k_ttft_ms": 3806.76,
      "tpot_slo_met": true
    },
    {
      "token_budget": 1024,
      "num_prefill_chunks": 99,
      "max_itl_ms": 26.6,
      "mean_itl_ms": 24.1,
      "short_chat_ttft_ms": 33.64,
      "doc_100k_ttft_ms": 2541.39,
      "tpot_slo_met": true
    },
    {
      "token_budget": 2048,
      "num_prefill_chunks": 49,
      "max_itl_ms": 46.63,
      "mean_itl_ms": 34.44,
      "short_chat_ttft_ms": 51.51,
      "doc_100k_ttft_ms": 1907.21,
      "tpot_slo_met": true
    },
    {
      "token_budget": 4096,
      "num_prefill_chunks": 25,
      "max_itl_ms": 79.26,
      "mean_itl_ms": 36.46,
      "short_chat_ttft_ms": 88.25,
      "doc_100k_ttft_ms": 1579.98,
      "tpot_slo_met": false
    },
    {
      "token_budget": 8192,
      "num_prefill_chunks": 13,
      "max_itl_ms": 144.22,
      "mean_itl_ms": 38.24,
      "short_chat_ttft_ms": 165.76,
      "doc_100k_ttft_ms": 1422.78,
      "tpot_slo_met": false
    }
  ]
}
