fly-apps/bumblebee-model-harness

Minimal Elixir application that can host AI models on Fly.io GPUs and make them available via WireGuard to remote clustered Elixir applications for improved development experiences.

37
/ 100
Emerging

This project offers a way for Elixir developers to quickly access powerful AI models like Llama 2, Zephyr, or Mistral, running on cloud GPUs. It allows your local Elixir application to send requests to a model hosted in the cloud, receiving AI-generated responses back. This is designed for Elixir developers who want to integrate large language models into their applications without managing complex GPU infrastructure locally.

No commits in the last 6 months.

Use this if you are an Elixir developer building an application that needs to use large AI models, and you want to keep your local development fast while offloading the heavy computation to cloud GPUs.

Not ideal if you are not an Elixir developer, or if your application doesn't require access to large language models.

Elixir-development AI-integration large-language-models cloud-deployment GPU-access
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

52

Forks

7

Language

Elixir

License

MIT

Category

llm-api-gateways

Last pushed

Apr 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/fly-apps/bumblebee-model-harness"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.