VectorInstitute/vector-inference

Efficient LLM inference on Slurm clusters.

49
/ 100
Emerging

This tool helps researchers and AI practitioners efficiently deploy and manage large language models (LLMs) on Slurm-managed computing clusters. You provide a model name, and it gives you a URL endpoint to send inference requests to, making it easy to generate text or responses from the model. This is ideal for anyone who needs to run LLM inference at scale within a shared cluster environment.

Use this if you need to quickly get an LLM inference server running on a Slurm cluster and get a live URL to send requests to.

Not ideal if you are working with a single machine or do not have access to a Slurm-managed cluster.

AI-research LLM-deployment high-performance-computing cluster-management model-serving
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

95

Forks

12

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/VectorInstitute/vector-inference"

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