+4
日增长
5,014
stars
894
forks
28
watchers
2,152
prs
1,269
issues
18
releases
README
English version | 中文版 | 日本語版 HAMi Kubernetes GPU virtualization and heterogeneous accelerator scheduling for AI infrastructure. !HAMi Architecture HAMi stands for Heterogeneous AI Computing Virtualization Middleware. Formerly known as k8s-vGPU-scheduler, HAMi helps platform teams share expensive GPUs and other AI accelerators across Kubernetes workloads, isolate device memory and compute, and schedule pods with device-aware policies without changing application code. HAMi is a CNCF Incubating and CNCF Landscape project. It is also listed in the CNAI Landscape. !CNCF logo Documentation - Architecture - GPU virtualization - Supported devices and vendor guides - Prerequisites - Install and run a first workload - Upgrade and migrate values - Configuration and operations - NVIDIA scheduling policies - NVIDIA dynamic MIG - Device allocation metrics - Device usage metrics - Grafana dashboards - WebUI - Volcano integration - Kueue integration - Benchmarks - Troubleshooting - Uninstall Repository resources - Chart values reference - Workload examples - Agent skills - HAMi-WebUI repository Roadmap, Governance, And Contributing HAMi is governed by maintainers and contributors. Governance is described in the HAMi community repository. To contribute code, documentation, tests, or device backend improvements, read CONTRIBUTING.md. Community For chat channels, mailing lists, meeting schedules, and meeting notes, visit the HAMi community page. Talk materials License HAMi is licensed under the Apache License 2.0. See LICENSE for details. Copyright Contributors to HAMi, established as HAMi a Series of LF Projects, LLC.
Top issues
#4Who's using HAMi 75 comments · 2021-12-20#2125[LFX Mentorship] Strengthen GPU memory isolation for child and SSH-started processes23 comments · 2026-07-24#2581Feature Request: google gVisor (runsc) compatibility for NVIDIA vGPU enforcement21 comments · 2026-08-11#2764HAMi v2.11 RoadMap13 comments · 2026-08-21#2126[LFX Mentorship] Improve HAMi GPU observability metrics and dashboards11 comments · 2026-07-24#3345GPU model(eg. H100..) names in migProfileAllowlist do not match NVML device names10 comments · 2026-11-02#3078vendor device plugins do not validate the allocation annotation9 comments · 2026-09-18#3073[Proposal] HAMi-aware fractional GPU cost attribution with OpenCost8 comments · 2026-09-18
Discussions
#2003Design discussion: sharing NVDEC/NVENC in multi‑tenant DeepStream pipelines .1 comments · 2026-07-03#1944Does the Hami v2.9.0 version support the glibc version for GPU nodes being 2.38?1 comments · 2026-06-11#1742HAMi 安装部署错误0 comments · 2026-04-10#1551Is there any plan for supporting kunlun XPU or XPU-r ?1 comments · 2025-12-22#1516difference between liangjw/kube-webhook & jettech/kube-webhook0 comments · 2025-12-04#1435kubevirt supports mdev,Does this tool support kubevirt ?0 comments · 2025-10-24#1389Does Hami support RKE2 when using Operator-gpu0 comments · 2025-10-08#1167Does HAMi support Talos Linux based K8s cluster?0 comments · 2025-07-08
Latest release
v2.11.0 v2.11.0 2026-11-04What's Changed Key Features General: No longer mount HAMI-core to whole GPU allocation, metrics will be exported by NVML directly Flexible-MIG Support Cluster Autoscaler Real-usage monitoring for Flexible-mig workloads Remote CUDA: Allows running vllm on remote cuda Schedule: PodGroup Support New schedule policy: mutex Schedule policy combinations GPU/CPU Numa Align Devices: Full AMD Support Ascend 950 Support libvnpu performance optimization ✨ Features Details ci: allow manual dispatch of the Trivy image scan by @moezdil in https://github.com/Project-