kserve / open-inference-protocol
Repository for open inference protocol specification
☆49Updated 7 months ago
Alternatives and similar repositories for open-inference-protocol:
Users that are interested in open-inference-protocol are comparing it to the libraries listed below
- Controller for ModelMesh☆224Updated 3 weeks ago
- Distributed Model Serving Framework☆158Updated last week
- User documentation for KServe.☆104Updated this week
- Kubernetes Operator, ansible playbooks, and production scripts for large-scale AIStore deployments on Kubernetes.☆89Updated this week
- Kubeflow Pipelines on Tekton☆178Updated 4 months ago
- Unified runtime-adapter image of the sidecar containers which run in the modelmesh pods☆21Updated last week
- ☆107Updated this week
- ☆112Updated last week
- kfctl is a CLI for deploying and managing Kubeflow☆184Updated last year
- JobSet: a k8s native API for distributed ML training and HPC workloads☆194Updated last week
- Unified specification for defining and executing ML workflows, making reproducibility, consistency, and governance easier across the ML p…☆91Updated 11 months ago
- An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.☆88Updated last week
- Helm charts for the KubeRay project☆43Updated this week
- A top-like tool for monitoring GPUs in a cluster☆86Updated last year
- Argoflow has been superseded by deployKF☆137Updated last year
- A curated list of awesome projects and resources related to Kubeflow (a CNCF incubating project)☆204Updated 3 months ago
- AWS virtual gpu device plugin provides capability to use smaller virtual gpus for your machine learning inference workloads☆204Updated last year
- Holistic job manager on Kubernetes☆112Updated last year
- MLOps Python Library☆117Updated 2 years ago
- LeaderWorkerSet: An API for deploying a group of pods as a unit of replication☆339Updated this week
- MLFlow Deployment Plugin for Ray Serve☆44Updated 2 years ago
- Cloud Native Benchmarking of Foundation Models☆24Updated 4 months ago
- Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.☆198Updated 2 months ago
- GenAI inference performance benchmarking tool☆19Updated last week
- Dynamic Resource Allocation (DRA) for NVIDIA GPUs in Kubernetes☆330Updated this week
- Module, Model, and Tensor Serialization/Deserialization☆217Updated last month
- Charmed Kubeflow☆108Updated 2 weeks ago
- ☆170Updated last week
- KServe models web UI☆36Updated last month
- Chassis turns machine learning models into portable container images that can run just about anywhere.☆86Updated 10 months ago