Try inference and training optimization. See what changes.

import json
from pyodide.http import pyfetch

response = await pyfetch(
    "https://api.reductionofstates.com/v1/demo/inference",
    method="POST",
    headers={"Content-Type": "application/json"},
    body=json.dumps({"prompt": "Explain KV caching."}),
    credentials="omit",
)
response.raise_for_status()
result = await response.json()
print(result["choices"][0]["message"]["content"])

const response = await fetch(
  "https://api.reductionofstates.com/v1/demo/inference",
  {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: "Explain KV caching." }),
    credentials: "omit",
  },
);
if (!response.ok) throw new Error(`Gateway returned ${response.status}`);
const result = await response.json();
console.log(result.choices[0].message.content);

curl https://api.reductionofstates.com/v1/demo/inference \
  -H 'Content-Type: application/json' \
  -d '{"prompt":"Explain KV caching."}'