makllama / makllama

Related projects: ⓘ

• InftyAI / llmaz
  ☸️ Easy, advanced inference platform for large language models on Kubernetes
  ☆15Updated this week
• BaizeAI / kcover
  ☆22Updated last week
• NVIDIA / knavigator
  knavigator is a development, testing, and optimization toolkit for AI/ML scheduling systems at scale on Kubernetes.
  ☆47Updated 3 weeks ago
• kerthcet / k8s-specific-knowledge-base
  A QA system based on k8s-specific knowledge build on ChatGLM2-6B, serving by Ray.
  ☆9Updated last year
• leptonai / gpud
  ☆158Updated this week
• elastic-ai / elastic-gpu-agent
  elastic-gpu-agent is a Kubernetes device plugin for GPU resources allocation on node.
  ☆54Updated 2 years ago
• dragonflyoss / helm-charts
  Dragonfly Helm Charts
  ☆30Updated last week
• alauda / alb
  ALB (Another Load Balancer) is a Kubernetes Gateway powered by OpenResty with years of production experience from Alauda.
  ☆59Updated last week
• NVIDIA / vgpu-device-manager
  NVIDIA vGPU Device Manager manages NVIDIA vGPU devices on top of Kubernetes
  ☆99Updated this week
• iomesh / charts
  IOMesh Helm Charts Repo
  ☆14Updated last month
• InftyAI / Awesome-LLMOps
  🎉 An awesome & curated list of best LLMOps tools.
  ☆17Updated last week
• elastic-ai / elastic-gpu-scheduler
  elastic-gpu-scheduler is a Kubernetes scheduler extender for GPU resources scheduling.
  ☆134Updated last year
• run-ai / fake-gpu-operator
  ☆57Updated 3 weeks ago
• NVIDIA / k8s-driver-manager
  The NVIDIA Driver Manager is a Kubernetes component which assist in seamless upgrades of NVIDIA Driver on each node of the cluster.
  ☆33Updated this week
• kubernetes-sigs / lws
  LeaderWorkerSet: An API for deploying a group of pods as a unit of replication
  ☆121Updated this week
• flame-sh / flame
  A distributed system for intelligent workload
  ☆19Updated 4 months ago
• nekomeowww / ollama-operator
  Yet another operator for running large language models on Kubernetes with ease. Powered by Ollama! 🐫
  ☆97Updated 3 weeks ago
• open-cluster-management-io / cluster-proxy
  An OCM addon that automates the installation of Kubernetes' konnectivity servers and agents.
  ☆42Updated last month
• k-cloud-labs / scheduler-stress-test
  A stress testing tool for the scheduler in a large-scale scenario.
  ☆14Updated 4 months ago
• copilot-io / runtime-copilot
  The main purpose of runtime copilot is to assist with node runtime management tasks such as configuring registries, upgrading versions, i…
  ☆12Updated last year
• kubernetes-sigs / jobset
  JobSet: a k8s native API for distributed ML training and HPC workloads
  ☆133Updated this week
• cwdsuzhou / super-scheduling
  a topology-scheduler and a descheduler extened from descheduler.
  ☆15Updated 3 years ago
• ahrtr / etcd-diagnosis
  A comprehensive tool for etcd diagnosis
  ☆25Updated this week
• openkruise / kruise-tools
  Tools to use with the Kruise libraries
  ☆43Updated 2 weeks ago
• tensorchord / envd-server
  Backend server for envd
  ☆21Updated 9 months ago
• kubeagi / arcadia
  A diverse, simple, and secure one-stop LLMOps platform
  ☆78Updated 4 months ago
• kubernetes-sigs / dra-example-driver
  Example DRA driver that developers can fork and modify to get them started writing their own.
  ☆46Updated this week
• kubevela / prism
  API Extensions for core KubeVela.
  ☆12Updated last week
• volcano-sh / resource-exporter
  Resource Exporter for volcano scheduling, e.g. NUMA-Aware scheduling.
  ☆16Updated 9 months ago
• knight42 / kopilot
  Your AI Kubernetes Expert
  ☆173Updated last year