Skip to content

Conversation

@rachfop
Copy link
Collaborator

@rachfop rachfop commented Dec 11, 2025

Towards DEVA-1068
Run:

pixi run max serve \
  --model openai-community/gpt2 \
  --custom-architectures gpt2_module_v3 \
  --port 8888

Then in another terminal run:

curl http://localhost:8888/v1/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai-community/gpt2",
    "prompt": "The future of AI",
    "max_tokens": 30
  }' | jq .

note: you can use a different port number or leave it out.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants