~/llamay $ llamay serve -m qwen2.5:0.5b -embed all-minilm:latest -addr 127.0.0.1:11439
time=2026-09-18T08:49:56.609-04:00 level=INFO msg="device graph attached" max-tokens=256
time=2026-09-18T08:49:56.624-04:00 level=INFO msg="encoder loaded" model=all-MiniLM-L6-v2 pa
th=~/.llamay/models/blobs/sha256-797b70c4edf85907fe0a49eb85811256f65fa0f7bf52166b147fd16be2b
e4662
time=2026-09-18T08:49:56.624-04:00 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
  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/embeddings -H 'content-type: application/json'
\
>   -d '{"model":"all-minilm:latest","input":["a local inference engine","a bicycle repair m
anual"]}' \
>   | jq '{model, n: (.data|length), dims: (.data[0].embedding|length)}'
{
  "model": "all-MiniLM-L6-v2",
  "n": 2,
  "dims": 384
}
~/llamay $ curl -s http://127.0.0.1:11439/v1/embeddings -H 'content-type: application/json'
\
>   -d '{"model":"all-minilm:latest","input":["hello"]}' | jq '.data[0].embedding[0:6]'
[
  -0.06279965,
  0.054916486,
  0.05200889,
  0.085709885,
  -0.082876645,
  -0.07456734
]