InftyAI / llmazLinks
βΈοΈ Easy, advanced inference platform for large language models on Kubernetes. π Star to support our work!
β228Updated last week
Alternatives and similar repositories for llmaz
Users that are interested in llmaz are comparing it to the libraries listed below
Sorting:
- LeaderWorkerSet: An API for deploying a group of pods as a unit of replicationβ529Updated this week
- A federation scheduler for multi-clusterβ48Updated last month
- Device-plugin for volcano vgpu which support hard resource isolationβ98Updated last month
- Large language model fine-tuning capabilities based on cloud native and distributed computing.β91Updated last year
- Device plugins for Volcano, e.g. GPUβ126Updated 4 months ago
- knavigator is a development, testing, and optimization toolkit for AI/ML scheduling systems at scale on Kubernetes.β69Updated 2 weeks ago
- π« A lightweight p2p-based cache system for model distributions on Kubernetes. Reframing now to make it an unified cache system with POSIβ¦β24Updated 8 months ago
- π§― Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.β31Updated this week
- Gateway API Inference Extensionβ423Updated this week
- HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in containerβ195Updated last week
- NVIDIA DRA Driver for GPUsβ402Updated this week
- a unified scheduler for online and offline tasksβ613Updated 4 months ago
- Using CRDs to manage GPU resources in Kubernetes.β206Updated 2 years ago
- β131Updated 2 weeks ago
- β283Updated this week
- JobSet: a k8s native API for distributed ML training and HPC workloadsβ249Updated this week
- The API (CRD) of Volcanoβ43Updated last month
- β119Updated 2 years ago
- elastic-gpu-scheduler is a Kubernetes scheduler extender for GPU resources scheduling.β142Updated 2 years ago
- The limitless expansion of Kubernetes. Make Kubernetes without boundariesβ230Updated last month
- Katalyst aims to provide a universal solution to help improve resource utilization and optimize the overall costs in the cloud. This is tβ¦β506Updated this week
- The Volcano Deschedulerβ17Updated 6 months ago
- Resource Exporter for volcano scheduling, e.g. NUMA-Aware scheduling.β17Updated 2 months ago
- A Cloud-Native Service Catalog and Full Lifecycle Management Platform accross Multi-cloud and Edgeβ34Updated last year
- Federated middleware based on Karmadaβ48Updated last year
- katalyst aims to provide a universal solution to help improve resource utilization and optimize the overall costs in the cloud. This repoβ¦β46Updated last week
- β44Updated last month
- KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scaleβ723Updated this week
- A kubernetes plugin which enables dynamically add or remove GPU resources for a running Podβ127Updated 3 years ago
- Go Abstraction for Allocating NVIDIA GPUs with Custom Policiesβ116Updated last month