{
  "ts": 1785314162.0283267,
  "mode": "dflash",
  "spec": {
    "type": "draft-dflash",
    "n_max": 7,
    "block_size": 16
  },
  "base_url": "http://127.0.0.1:8000/v1",
  "model": "local-laguna",
  "rows": [
    {
      "label": "gen8_short",
      "prompt_tokens": 48,
      "completion_tokens": 3,
      "latency_s": 0.483,
      "tok_s": 6.212,
      "content_head": "OK"
    },
    {
      "label": "gen128",
      "prompt_tokens": 58,
      "completion_tokens": 128,
      "latency_s": 8.374,
      "tok_s": 15.286,
      "content_head": "Speculative decoding is a model inference optimization technique that accelerates text generation by using a fast, light"
    },
    {
      "label": "gen256",
      "prompt_tokens": 61,
      "completion_tokens": 256,
      "latency_s": 14.762,
      "tok_s": 17.342,
      "content_head": "## Block-Diffusion vs EAGLE-3: Practical Serving Comparison\n\n### **Block-Diffusion Draft Models**\n\n**What it is:** Uses "
    }
  ],
  "schema": "laguna.dflash_throughput/v1"
}