import { estimateTpot, DEFAULT_ARCHITECTURES, DEFAULT_GPU_SPECS } from "@agentium/core";

const tpot = estimateTpot(
  DEFAULT_ARCHITECTURES["llama-3.1-70b"],
  4096,    // 4K context
  1,       // batch size
  { gpu: DEFAULT_GPU_SPECS["h100-sxm"], gpuCount: 4, nandPerGpuGb: 0, nandBandwidthGBs: 7 },
  "fp8",
);
// → milliseconds per output token

import { estimateTtft } from "@agentium/core";

// Single user
estimateTtft(llama70b, 4096, 1, hw);   // fast — just one prefill

// 20 concurrent users
estimateTtft(llama70b, 4096, 20, hw);  // 10× worse — queue serialization

import { singlePrefillMs } from "@agentium/core";

singlePrefillMs(llama70b, 4096, hw);    // ~16ms on 4× H100
singlePrefillMs(llama70b, 32768, hw);   // much longer — quadratic attention

import { ttftBreachPoint } from "@agentium/core";

const breach = ttftBreachPoint(llama70b, hw, 5000, 4096);
// → e.g. 629 users before 5s SLA breach

// More GPUs push the breach point out
const breach8gpu = ttftBreachPoint(llama70b, { ...hw, gpuCount: 8 }, 5000);
// → higher number — more TFLOPS

import { restoreLatency } from "@agentium/core";

restoreLatency(40, 7);     // 40 GB at Gen4 (7 GB/s) → 5,714ms
restoreLatency(40, 14);    // 40 GB at Gen5 (14 GB/s) → 2,857ms
restoreLatency(40, 7, 4);  // 4 parallel streams → 22,857ms per stream