Project-HAMi/HAMi

Add values.schema.json to the Helm chart for install-time values validation about 1 hour ago

good first issue kind/feature

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Title: device-plugin: RegisterInAnnotation() caches the new device digest before the node patch succeeds, permanently skipping retries after a transient failure about 1 hour ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

[bug]: ascend MutateAdmission panics on nil Requests (assignment to nil map) about 2 hours ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

ResourceQuota is unenforced while an update is applied: onUpdateQuota zeroes limits before restoring them 1 day ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Missing Test for InitContainers & EphemeralContainers GPU Quota Checks 2 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Nil Pointer Dereference in Scheduler HTTP Endpoint Handlers 3 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

bug(quota): FitQuota treats an explicit zero limit as unlimited, so ResourceQuota "0" allows all GPU usage 3 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

fix(scheduler): node informer missing UpdateFunc delays annotation re-registration 3 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

fix(scheduler): PredicateRoute ignores checkBody and panics on nil body 3 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

fix(awsneuron): nil CustomInfo write can panic in Fit/AddResourceUsage 3 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

bug(quota): DelQuota uses length check instead of HasPrefix matching AddQuota 5 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

[Bug] Leader election isHolderOf false positive when hostname is a prefix of another node's hostname 5 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

[bug]: mthreads MutateAdmission panics on nil maps (nil Annotations / nil Limits) 5 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

issue-translate misclassifies technical English titles as French 6 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

ResourceQuota tombstone deletion leaves stale device limits in scheduler cache 6 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Scheduler memory allocation ratio becomes NaN for devices with zero total memory 8 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

bug: Init-container-only accelerator requests bypass admission mutation and quota checks 9 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

[Bug] Mutating webhook allows pods with privileged containers when other containers request GPU resources 11 days ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Does hami have any plans to support remote GPU calls? 24 days ago

good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Fix code scanning alert - encoding/gob: golang: Calling Decoder.Decode on a message which contains deeply nested structures... 4 months ago

good first issue Stale

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Fix code scanning alert - encoding/gob: golang: Calling Decoder.Decode on a message which contains deeply nested structures... 4 months ago

good first issue Stale

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

[Call to action] UT coverage improvement task 4 months ago

good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

[Scheduler Policy Bug] hami.io/gpu-scheduler-policy (spread/binpack) functionality is reversed 7 months ago

kind/bug good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Refactor the impl of pkg/util/nodelock to remove dependency on `update` verb about 1 year ago

AI Summary: Refactor the `pkg/util/nodelock` package in the HAMi Kubernetes scheduler to replace the `Update` verb with `Patch` for updating node annotations, ensuring no behavioral changes and passing existing tests. This involves researching the feasibility of using `Patch`, refactoring the code, and updating the relevant Kubernetes cluster role definition.

Complexity: 3/5

kind/enhancement good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Improve the impl of DevicePluginConfigs.Nodeconfig overwriting NvidiaConfig about 1 year ago

AI Summary: Refactor the `readFromConfigFile` function in `pkg/device/nvidia/device.go` to improve the handling of configuration overwriting. Specifically, address inconsistencies between `NvidiaConfig` and `DevicePluginConfigs.Nodeconfig` fields, ensuring that all relevant configuration options are explicitly defined and handled in a clear and maintainable way. This involves potentially adding missing fields to `Nodeconfig` and modifying the logic to correctly handle all configuration options.

Complexity: 4/5

kind/enhancement good first issue

Project-HAMi/HAMi

3.7K

Heterogeneous GPU Sharing on Kubernetes

Go

#ascend#cambricon#cncf#device-plugin#gpu-acceleration#gpu-management#gpu-shareable#gpu-virtualization#hygon#iluvatar#kubernetes#kubernetes-gpu-cluster#metax#mthreads#nvidia#vgpu#vgpu-hypervisor

Open Issues Need Help