# Project-HAMi/HAMi

Heterogeneous GPU Sharing on Kubernetes

Repository: https://github.com/Project-HAMi/HAMi
Canonical: https://ross.abutalabs.com/products/hami
Homepage: https://project-hami.io
Language: Go
License: Apache-2.0
License Family: permissive
Topics: vgpu, gpu-virtualization, device-plugin, gpu-management, kubernetes-gpu-cluster, ascend, cambricon, gpu-shareable, kubernetes, metax, nvidia, hygon, iluvatar, mthreads, cncf, gpu-acceleration, vgpu-hypervisor
Last push: 2026-08-26T03:27:50+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 86, longevity 100
- inputs: {"age_days": 1814, "days_push": 7, "days_rel": 12, "gap_med": 47, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4438, forks 794 (observed 2026-08-28T04:08:49.314738+00:00)

## What it is
HAMi (Heterogeneous AI Computing Virtualization Middleware) is a CNCF Incubating, Kubernetes-native GPU virtualization and scheduling middleware that lets multiple workloads share GPUs and other AI accelerators with hard memory/compute isolation. It works via device plugins, a mutating webhook, and a custom scheduler, supporting NVIDIA, Ascend, Cambricon, Hygon, and other vendors without application code changes.

## Use cases
- share one GPU across multiple Kubernetes pods
- slice GPU memory for AI inference workloads
- schedule heterogeneous accelerators like NPU and MLU in Kubernetes
- prevent one pod from OOMing other tasks on a shared GPU
- improve GPU utilization in an AI cluster
- allocate fractional GPU resources (e.g. 1/2 or 1/4 of a card) to jobs
- monitor GPU memory and core usage across vendors

## When to choose
- you run Kubernetes with expensive GPUs that are underutilized by exclusive allocation
- you need VRAM/compute isolation for shared GPUs without MIG-capable hardware
- you manage mixed-vendor accelerators (NVIDIA, Ascend, Cambricon, Hygon, etc.) and want one scheduling workflow
- you want device-aware scheduling policies like binpack, spread, or topology-aware placement

## When to avoid
- you need hardware-level isolation guarantees such as NVIDIA MIG on A100/H100
- your cluster is not Kubernetes-based
- you only run a single workload per GPU and don't need sharing
- you require vendor-official support rather than a community middleware layer

## Facets
- artifact type: service
- maturity: active
- function: container-orchestration, scheduling, monitoring, gpu-computing
- domain: cloud-computing, gpu-computing, infrastructure-as-code, machine-learning
- platform: go, self-hosted
- tags: gpu-virtualization, vgpu, device-plugin, gpu-sharing, heterogeneous-accelerators, cncf, ai-infrastructure, gpu-scheduling, nvidia, ascend, cambricon, containers, kubernetes, linux, docker

## Member repositories
- Project-HAMi/HAMi (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:49.314738+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:51.105801+00:00, confidence not recorded.
  - readme: https://github.com/Project-HAMi/HAMi (fetched 2026-08-28T04:08:49.314738+00:00, sha 3b9fdd7bc80f)
  - homepage: https://project-hami.io (fetched 2026-08-29T09:08:08.473541+00:00, sha b7821d2f989b)
  - site_page: https://project-hami.io/docs/userguide/device-supported (fetched 2026-08-29T09:08:08.487666+00:00, sha 8754d0f64ad8)
  - site_page: https://project-hami.io/docs/core-concepts/gpu-virtualization (fetched 2026-08-29T09:08:08.489203+00:00, sha 136c47637cfa)
  - site_page: https://project-hami.io/docs (fetched 2026-08-29T09:08:08.482819+00:00, sha 47e99a283b4c)
  - site_page: https://project-hami.io/docs/get-started/deploy-with-helm (fetched 2026-08-29T09:08:08.486097+00:00, sha 5fe813d69a05)
  - site_page: https://project-hami.io/changelog (fetched 2026-08-29T09:08:08.484547+00:00, sha 8c9a7e085843)
- Data as of 2026-08-30T08:39:29.467469+00:00.