HAMi

Input—per 1M tokens

Output—per 1M tokens

Context—tokens

WeightsClosed

About

HAMi is ranked #11 of 21 in GPU cluster management software on Inferse. It runs on Linux, Self-hosted. There is a free plan.

Compared on GPU cluster management software

Free plan: Yesproject-hami.io
Deployment model: self_hostedproject-hami.io
Workload scheduling: bothproject-hami.io
Kubernetes support: Yesproject-hami.io
Quota controls: Yesproject-hami.io
GPU utilization metrics: Yesproject-hami.io
Cloud GPU support: Yesproject-hami.io

Facts

Product: HAMi is open-source GPU virtualization middleware that enables sharing, isolation and scheduling of heterogeneous accelerators for AI workloads on Kubernetes.project-hami.io · 3 Oct 2026
Resource slicing: HAMi lets workloads request GPU memory and core limits using Kubernetes resource limits such as `nvidia.com/gpumem` and `nvidia.com/gpucores`.project-hami.io · 3 Oct 2026
Scheduling: Scheduling policies include binpack, spread and numa-first; binpack and spread can also be selected at node or GPU scope.project-hami.io · 3 Oct 2026
Accelerators: The project lists support for NVIDIA, AWS Neuron, Huawei Ascend, Cambricon, Enflame, Hygon, Iluvatar, Kunlunxin, MetaX, Moore Threads, Vastai, AMD and Biren accelerators.project-hami.io · 3 Oct 2026
Integrations: The site lists Kubernetes, Volcano, Kueue, Koordinator and KAI Scheduler in its Kubernetes scheduling ecosystem.project-hami.io · 3 Oct 2026
Monitoring: HAMi exposes real-time device memory and core utilization metrics at a node metrics endpoint that can be scraped by Prometheus.project-hami.io · 3 Oct 2026
Deployment requirements: Classic HAMi supports Kubernetes v1.23 or later; HAMi-DRA requires Kubernetes v1.34 or later with the DRA Consumable Capacity feature gate enabled, CDI and NVIDIA driver 440 or later.project-hami.io · 3 Oct 2026
Isolation mechanism: For NVIDIA devices, HAMi enforces limits through user-space library interception; the FAQ says applications that bypass the CUDA library are not covered.project-hami.io · 3 Oct 2026
Isolation limits: The FAQ characterizes HAMi vGPU memory and compute enforcement as soft and best-effort, and recommends MIG when hardware-enforced isolation is required for compliance or SLAs.project-hami.io · 3 Oct 2026
Scheduling limit: HAMi's built-in priority field supports two levels; the FAQ recommends integrating Volcano for multi-level queue priorities.project-hami.io · 3 Oct 2026
Support: The site links to documentation, tutorials, Discord and the `#hami-dev` Slack channel for community resources.project-hami.io · 3 Oct 2026
Project status: HAMi was accepted as a CNCF Incubating project on July 2, 2026.project-hami.io · 3 Oct 2026
Purpose: HAMi is open-source, cloud-native GPU virtualization middleware for sharing, isolating, and scheduling heterogeneous accelerators on Kubernetes.project-hami.io · 4 Oct 2026
Resource controls: HAMi supports GPU memory and compute quotas, with hard runtime isolation for supported devices.project-hami.io · 4 Oct 2026
Scheduling: HAMi offers binpack, spread, and topology-aware scheduling policies.project-hami.io · 4 Oct 2026
Device coverage: The v2.10.0 supported-device matrix lists NVIDIA, Cambricon, Hygon, Huawei Ascend, Iluvatar, Mthreads, MetaX, Enflame, Kunlunxin, Vastai, AMD, AWS Neuron, and Biren devices as stable.project-hami.io · 4 Oct 2026
Kubernetes integration: HAMi works with Kubernetes APIs, DRA, and CDI.project-hami.io · 4 Oct 2026
Deployment: The quick start installs HAMi with Helm and requires Kubernetes, Helm, kubectl, and installation permissions.project-hami.io · 4 Oct 2026
Ecosystem integrations: The project documents integrations with Volcano, Kueue, Koordinator, and NVIDIA KAI Scheduler.project-hami.io · 4 Oct 2026
Monitoring: HAMi provides allocation counts and spread plus real-time GPU memory and core utilization visibility.project-hami.io · 4 Oct 2026
Workloads: The site identifies LLM, machine-learning, and HPC workloads as use cases.project-hami.io · 4 Oct 2026
Project status: HAMi is a CNCF Incubating project.project-hami.io · 4 Oct 2026
Limitations: The supported-device matrix marks memory isolation, core isolation, and multi-card partitioning as unavailable for some listed devices.project-hami.io · 4 Oct 2026
Community support: The project links to community support through Discord and Slack (#hami-dev).project-hami.io · 4 Oct 2026