rh-aiservices-bu / gpu-partitioning-guideLinks
Repository to demo GPU Sharing with Time Slicing, MPS, MIG and others
☆50Updated last year
Alternatives and similar repositories for gpu-partitioning-guide
Users that are interested in gpu-partitioning-guide are comparing it to the libraries listed below
Sorting:
- InstaSlice Operator facilitates slicing of accelerators using stable APIs☆47Updated this week
- Cloud Native Artifacial Intelligence Model Format Specification☆116Updated this week
- Example DRA driver that developers can fork and modify to get them started writing their own.☆105Updated 3 weeks ago
- GenAI inference performance benchmarking tool☆123Updated this week
- Open Data Hub operator to manage ODH component integrations☆89Updated this week
- An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.☆134Updated last week
- open-cluster-management governance material.☆64Updated 3 weeks ago
- Holistic job manager on Kubernetes☆116Updated last year
- The kernel module management operator builds, signs and loads kernel modules in Kubernetes clusters.☆109Updated this week
- This project makes running the InstructLab large language model (LLM) fine-tuning process easy and flexible on OpenShift☆27Updated 2 months ago
- Model Registry provides a single pane of glass for ML model developers to index and manage models, versions, and ML artifacts metadata. I…☆150Updated this week
- llm-d helm charts and deployment examples☆46Updated last month
- A collection of community maintained NRI plugins☆95Updated last week
- JobSet: a k8s native API for distributed ML training and HPC workloads☆279Updated last week
- Resources, demos, recipes,... to work with LLMs on OpenShift with OpenShift AI or Open Data Hub.☆139Updated 2 months ago
- Simplified model deployment on llm-d☆27Updated 4 months ago
- InstaSlice facilitates the use of Dynamic Resource Allocation (DRA) on Kubernetes clusters for GPU sharing☆30Updated 11 months ago
- ☆20Updated last week
- Enabling Kubernetes to make pod placement decisions with platform intelligence.☆176Updated 9 months ago
- ☆87Updated last year
- ☆17Updated last week
- DOCA Platform manages provisioning and service orchestration for Bluefield DPUs☆59Updated 3 weeks ago
- ☆32Updated last week
- ☆30Updated 2 months ago
- Operator for NooBaa - object data service for hybrid and multi cloud environments☆118Updated this week
- Gateway API Inference Extension☆524Updated this week
- A global load balancer operator for OpenShift☆55Updated last year
- CNI DRA Driver☆30Updated last month
- NVIDIA Network Operator☆292Updated this week
- ☆62Updated last year