#178 · Primary category： Inference & Local Deploy
budgetml
Deploy a ML inference service on a budget in less than 10 lines of code.
Project last updated：02/12/24
GitHub Stars
1.3K
Forks
65
Contributors
5
License
Apache-2.0
Why we included this project
BudgetML answers a question many practitioners have: how do I get a single model behind a secure HTTPS endpoint without learning Docker, Kubernetes, and TLS setup? It bundles FastAPI, LetsEncrypt certificates, OAuth2 auth, and GCP preemptible instances into a short launch call, so you can turn a Python Predictor class into a Swagger-documented API in minutes and cut compute costs by about 80%. That's the honest pitch: the authors say it's not for full production, and the repo hasn't been maintained lately, so treat it as a reference or starting point. For demos, internal tools, or quick prototypes on GCP, the approach and the code are still worth studying.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.