feat: use HAMi with nvshare as GPU plugin (#1033)
This commit is contained in:
@@ -0,0 +1,203 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: {{ include "hami-vgpu.scheduler" . }}-device
|
||||
labels:
|
||||
app.kubernetes.io/component: hami-scheduler
|
||||
{{- include "hami-vgpu.labels" . | nindent 4 }}
|
||||
data:
|
||||
device-config.yaml: |-
|
||||
{{- if .Files.Glob "files/device-config.yaml" }}
|
||||
{{- .Files.Get "files/device-config.yaml" | nindent 4}}
|
||||
{{- else }}
|
||||
nvidia:
|
||||
resourceCountName: {{ .Values.resourceName }}
|
||||
resourceMemoryName: {{ .Values.resourceMem }}
|
||||
resourceMemoryPercentageName: {{ .Values.resourceMemPercentage }}
|
||||
resourceCoreName: {{ .Values.resourceCores }}
|
||||
resourcePriorityName: {{ .Values.resourcePriority }}
|
||||
overwriteEnv: false
|
||||
defaultMemory: 16000
|
||||
defaultCores: 0
|
||||
defaultGPUNum: 1
|
||||
deviceSplitCount: {{ .Values.devicePlugin.deviceSplitCount }}
|
||||
deviceMemoryScaling: {{ .Values.devicePlugin.deviceMemoryScaling }}
|
||||
deviceCoreScaling: {{ .Values.devicePlugin.deviceCoreScaling }}
|
||||
gpuCorePolicy: {{ .Values.devices.nvidia.gpuCorePolicy }}
|
||||
knownMigGeometries:
|
||||
- models: [ "A30" ]
|
||||
allowedGeometries:
|
||||
-
|
||||
- name: 1g.6gb
|
||||
memory: 6144
|
||||
count: 4
|
||||
-
|
||||
- name: 2g.12gb
|
||||
memory: 12288
|
||||
count: 2
|
||||
-
|
||||
- name: 4g.24gb
|
||||
memory: 24576
|
||||
count: 1
|
||||
- models: [ "A100-SXM4-40GB", "A100-40GB-PCIe", "A100-PCIE-40GB", "A100-SXM4-40GB" ]
|
||||
allowedGeometries:
|
||||
-
|
||||
- name: 1g.5gb
|
||||
memory: 5120
|
||||
count: 7
|
||||
-
|
||||
- name: 2g.10gb
|
||||
memory: 10240
|
||||
count: 3
|
||||
- name: 1g.5gb
|
||||
memory: 5120
|
||||
count: 1
|
||||
-
|
||||
- name: 3g.20gb
|
||||
memory: 20480
|
||||
count: 2
|
||||
-
|
||||
- name: 7g.40gb
|
||||
memory: 40960
|
||||
count: 1
|
||||
- models: [ "A100-SXM4-80GB", "A100-80GB-PCIe", "A100-PCIE-80GB"]
|
||||
allowedGeometries:
|
||||
-
|
||||
- name: 1g.10gb
|
||||
memory: 10240
|
||||
count: 7
|
||||
-
|
||||
- name: 2g.20gb
|
||||
memory: 20480
|
||||
count: 3
|
||||
- name: 1g.10gb
|
||||
memory: 10240
|
||||
count: 1
|
||||
-
|
||||
- name: 3g.40gb
|
||||
memory: 40960
|
||||
count: 2
|
||||
-
|
||||
- name: 7g.79gb
|
||||
memory: 80896
|
||||
count: 1
|
||||
cambricon:
|
||||
resourceCountName: {{ .Values.mluResourceName }}
|
||||
resourceMemoryName: {{ .Values.mluResourceMem }}
|
||||
resourceCoreName: {{ .Values.mluResourceCores }}
|
||||
hygon:
|
||||
resourceCountName: {{ .Values.dcuResourceName }}
|
||||
resourceMemoryName: {{ .Values.dcuResourceMem }}
|
||||
resourceCoreName: {{ .Values.dcuResourceCores }}
|
||||
metax:
|
||||
resourceCountName: "metax-tech.com/gpu"
|
||||
|
||||
resourceVCountName: {{ .Values.metaxResourceName }}
|
||||
resourceVMemoryName: {{ .Values.metaxResourceMem }}
|
||||
resourceVCoreName: {{ .Values.metaxResourceCore }}
|
||||
mthreads:
|
||||
resourceCountName: "mthreads.com/vgpu"
|
||||
resourceMemoryName: "mthreads.com/sgpu-memory"
|
||||
resourceCoreName: "mthreads.com/sgpu-core"
|
||||
iluvatar:
|
||||
resourceCountName: {{ .Values.iluvatarResourceName }}
|
||||
resourceMemoryName: {{ .Values.iluvatarResourceMem }}
|
||||
resourceCoreName: {{ .Values.iluvatarResourceCore }}
|
||||
vnpus:
|
||||
- chipName: 910B
|
||||
commonWord: Ascend910A
|
||||
resourceName: huawei.com/Ascend910A
|
||||
resourceMemoryName: huawei.com/Ascend910A-memory
|
||||
memoryAllocatable: 32768
|
||||
memoryCapacity: 32768
|
||||
aiCore: 30
|
||||
templates:
|
||||
- name: vir02
|
||||
memory: 2184
|
||||
aiCore: 2
|
||||
- name: vir04
|
||||
memory: 4369
|
||||
aiCore: 4
|
||||
- name: vir08
|
||||
memory: 8738
|
||||
aiCore: 8
|
||||
- name: vir16
|
||||
memory: 17476
|
||||
aiCore: 16
|
||||
- chipName: 910B2
|
||||
commonWord: Ascend910B2
|
||||
resourceName: huawei.com/Ascend910B2
|
||||
resourceMemoryName: huawei.com/Ascend910B2-memory
|
||||
memoryAllocatable: 65536
|
||||
memoryCapacity: 65536
|
||||
aiCore: 24
|
||||
aiCPU: 6
|
||||
templates:
|
||||
- name: vir03_1c_8g
|
||||
memory: 8192
|
||||
aiCore: 3
|
||||
aiCPU: 1
|
||||
- name: vir06_1c_16g
|
||||
memory: 16384
|
||||
aiCore: 6
|
||||
aiCPU: 1
|
||||
- name: vir12_3c_32g
|
||||
memory: 32768
|
||||
aiCore: 12
|
||||
aiCPU: 3
|
||||
- chipName: 910B3
|
||||
commonWord: Ascend910B
|
||||
resourceName: huawei.com/Ascend910B
|
||||
resourceMemoryName: huawei.com/Ascend910B-memory
|
||||
memoryAllocatable: 65536
|
||||
memoryCapacity: 65536
|
||||
aiCore: 20
|
||||
aiCPU: 7
|
||||
templates:
|
||||
- name: vir05_1c_16g
|
||||
memory: 16384
|
||||
aiCore: 5
|
||||
aiCPU: 1
|
||||
- name: vir10_3c_32g
|
||||
memory: 32768
|
||||
aiCore: 10
|
||||
aiCPU: 3
|
||||
- chipName: 910B4
|
||||
commonWord: Ascend910B4
|
||||
resourceName: huawei.com/Ascend910B4
|
||||
resourceMemoryName: huawei.com/Ascend910B4-memory
|
||||
memoryAllocatable: 32768
|
||||
memoryCapacity: 32768
|
||||
aiCore: 20
|
||||
aiCPU: 7
|
||||
templates:
|
||||
- name: vir05_1c_8g
|
||||
memory: 8192
|
||||
aiCore: 5
|
||||
aiCPU: 1
|
||||
- name: vir10_3c_16g
|
||||
memory: 16384
|
||||
aiCore: 10
|
||||
aiCPU: 3
|
||||
- chipName: 310P3
|
||||
commonWord: Ascend310P
|
||||
resourceName: huawei.com/Ascend310P
|
||||
resourceMemoryName: huawei.com/Ascend310P-memory
|
||||
memoryAllocatable: 21527
|
||||
memoryCapacity: 24576
|
||||
aiCore: 8
|
||||
aiCPU: 7
|
||||
templates:
|
||||
- name: vir01
|
||||
memory: 3072
|
||||
aiCore: 1
|
||||
aiCPU: 1
|
||||
- name: vir02
|
||||
memory: 6144
|
||||
aiCore: 2
|
||||
aiCPU: 2
|
||||
- name: vir04
|
||||
memory: 12288
|
||||
aiCore: 4
|
||||
aiCPU: 4
|
||||
{{ end }}
|
||||
Reference in New Issue
Block a user