Cost-effective GPU workload optimisation on AWS using Kubernates and Spot Instances. Run AI workloads efficiently without breaking the bank!
-
Updated
Apr 26, 2025 - Python
#
nvidia-mig
Here are 4 public repositories matching this topic...
Kubernetes x NVIDIA DRA Workshop
-
Updated
Apr 17, 2026 - Shell
This project provides a fully-integrated local AI (LLM) deployment, ready to bring up with a simple `./llm.sh` command. It handles various modes of operation.
docker cpu docker-compose amd https nvidia whisper kokoro rag local-llm ollama open-webui private-ai self-hosted-ai kokoro-tts nvidia-mig security-first local-llm-ollama
-
Updated
Aug 28, 2026 - Python
Add this topic to your repo
To associate your repository with the nvidia-mig topic, visit your repo's landing page and select "manage topics."