InftyAI / llmaz
βΈοΈ Easy, advanced inference platform for large language models on Kubernetes. π Star to support our work!
β127Updated this week
Alternatives and similar repositories for llmaz:
Users that are interested in llmaz are comparing it to the libraries listed below
- π§― Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.β29Updated 4 months ago
- Device-plugin for volcano vgpu which support hard resource isolationβ72Updated last month
- A federation scheduler for multi-clusterβ37Updated 2 months ago
- Large language model fine-tuning capabilities based on cloud native and distributed computing.β92Updated last year
- π« A lightweight p2p-based cache system for model distributions on Kubernetes. Reframing now to make it an unified cache system with POSIβ¦β21Updated 4 months ago
- Device plugins for Volcano, e.g. GPUβ118Updated last month
- LeaderWorkerSet: An API for deploying a group of pods as a unit of replicationβ402Updated last week
- knavigator is a development, testing, and optimization toolkit for AI/ML scheduling systems at scale on Kubernetes.β65Updated last week
- Gateway API Inference Extensionβ243Updated this week
- π An awesome & curated list of best LLMOps tools.β87Updated this week
- A Cloud-Native Service Catalog and Full Lifecycle Management Platform accross Multi-cloud and Edgeβ33Updated last year
- Example DRA driver that developers can fork and modify to get them started writing their own.β69Updated last month
- The API (CRD) of Volcanoβ37Updated 2 weeks ago
- Federated middleware based on Karmadaβ48Updated last year
- JobSet: a k8s native API for distributed ML training and HPC workloadsβ219Updated this week
- Using CRDs to manage GPU resources in Kubernetes.β199Updated 2 years ago
- β114Updated 2 years ago
- katalyst aims to provide a universal solution to help improve resource utilization and optimize the overall costs in the cloud. This repoβ¦β43Updated last week
- elastic-gpu-scheduler is a Kubernetes scheduler extender for GPU resources scheduling.β140Updated 2 years ago
- β107Updated last month
- Fleetboard establishes an independent and unified parallel network, facilitating cross-cluster service discovery even in cases of IP overβ¦β27Updated last month
- GenAI inference performance benchmarking toolβ39Updated 3 weeks ago
- ControllerMesh is a solution that helps developers manage their controllers/operators better with enhanced isolation.β64Updated last year
- This project is designed to simulate GPU information, making it easier to test scenarios where a GPU is not available.β43Updated last month
- β12Updated 2 weeks ago
- Declarative Workflow of KubeVela which can run as standalone.β120Updated last week
- β246Updated 2 weeks ago
- Multi-cluster api gateway based on apiserver-aggregation.β102Updated 4 months ago
- The Volcano Deschedulerβ14Updated 3 months ago
- OpenCIDN (Open Container Image Deliver Network)β13Updated last week