~/llamay $ llamay serve -m qwen2.5:0.5b -addr 127.0.0.1:11439
time=2026-09-18T08:49:07.893-04:00 level=INFO msg="device graph attached" max-tokens=256
time=2026-09-18T08:49:07.894-04:00 level=INFO msg="llamay serving" addr=127.0.0.1:11439 mode
l=qwen2.5:0.5b arch=qwen2 max-loaded=2 keepalive=5m0s params="0.36 GB" context=32768 threads
=7 kv=f32 lexicon=0

  OpenAI      POST http://127.0.0.1:11439/v1/chat/completions
  Anthropic   POST http://127.0.0.1:11439/v1/messages
  Embeddings  POST http://127.0.0.1:11439/v1/embeddings     (start with -embed <encoder.gguf
>)
  Rerank      POST http://127.0.0.1:11439/rerank            (start with -rerank <reranker.gg
uf>)
  Contexts    POST http://127.0.0.1:11439/v1/contexts        (then /{id}/fork?n=8, /{id}/sna
pshot)
  Models      POST http://127.0.0.1:11439/api/pull          (and /api/copy, /api/delete)
  Stats       GET  http://127.0.0.1:11439/v1/stats


~/llamay $ # the server stays up; the rest of this is a second terminal
~/llamay $ curl -s http://127.0.0.1:11439/v1/contexts -H 'content-type: application/json' \
>   -d '{"model":"qwen2.5:0.5b","prompt":"You are a careful code reviewer."}' | jq
{
  "created": 1789735748,
  "id": "ctx_1",
  "pages": 1,
  "parent": "",
  "shared_pages": 0,
  "tokens": 7
}
~/llamay $ curl -s http://127.0.0.1:11439/v1/contexts | jq
{
  "data": [
    {
      "created": 1789735748,
      "id": "ctx_1",
      "pages": 1,
      "parent": "",
      "shared_pages": 0,
      "tokens": 7
    }
  ]
}
~/llamay $ # fork the one that exists, four ways
~/llamay $ ID=$(curl -s http://127.0.0.1:11439/v1/contexts | jq -r '.data[0].id') && \
>   curl -s http://127.0.0.1:11439/v1/contexts/$ID/fork -H 'content-type: application/json'
\
>   -d '{"n":4}' | jq
{
  "data": [
    {
      "created": 1789735748,
      "id": "ctx_2",
      "pages": 1,
      "parent": "ctx_1",
      "shared_pages": 1,
      "tokens": 7
    }
  ],
  "fork_ms": 0.009
}
~/llamay $ curl -s http://127.0.0.1:11439/v1/contexts | jq '.data | length'
2