Pinned Loading

1. llm-on-openshift llm-on-openshift Public

   Resources, demos, recipes,... to work with LLMs on OpenShift with OpenShift AI or Open Data Hub.

   Python 146 140

2. multi-gpu-llms multi-gpu-llms Public

   Repository to deploy LLMs with Multi-GPUs in distributed Kubernetes nodes

   Jupyter Notebook 30 13

3. gpu-partitioning-guide gpu-partitioning-guide Public

   Repository to demo GPU Sharing with Time Slicing, MPS, MIG and others

   Jupyter Notebook 60 14

4. litemaas litemaas Public

   LiteMaaS is a proof-of-concept application for managing LLM subscriptions, API keys, and usage tracking. It seamlessly integrates with LiteLLM to provide a unified interface for accessing multiple …

   TypeScript 56 26

5. sardeenz sardeenz Public

   Sardeenz is a proof-of-concept application that allows you to load more than one model on a given GPU. It allows you to add more and more models onto a GPU, until it is fully utilized.

   TypeScript 38 6

6. dynamic-model-autoscaling dynamic-model-autoscaling Public

   Dynamic Model Autoscaling

   Shell 3 1