🦄 Distributed Inference on Kubernetes with DRA and MIG
-
Updated
Sep 21, 2024 - Shell
#
multi-instance-gpu
Here are 7 public repositories matching this topic...
Unofficial example on creating Multi-Instance GPU (MIG) instances with NVIDIA Management Library (NVML) Go bindings.
-
Updated
Jan 16, 2025 - Go
Unofficial minimal instructions for managing NVIDIA Multi-Instance GPU (MIG) in a docker container
-
Updated
Jan 16, 2025
Tools for training, analysis and execution of an optimized task scheduling RL agent on GPUs with Multi-Instance GPU (MIG).
-
Updated
Jul 10, 2025 - Python
A Kubernetes serving manager for machine learning inference system enabled with NVIDIA MIG/MPS GPU-Sharing support
go docker kubernetes golang nvidia k8s mps nvidia-gpu mlops knative knative-serving multi-instance-gpu
-
Updated
Jul 2, 2025 - Go
C++ implementation of FAR scheduler, an approach for optimized GPU co-execution of tasks using the hardware-level partitioning MIG (Multi-Instance GPU).
-
Updated
Jan 24, 2025 - C++
A Kubernetes serving manager for machine learning inference system enabled with NVIDIA MIG/MPS GPU-Sharing support
-
Updated
Jul 17, 2025 - Go
Improve this page
Add a description, image, and links to the multi-instance-gpu topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the multi-instance-gpu topic, visit your repo's landing page and select "manage topics."