You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: netapp_dataops_k8s/docs/inference_server_management.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -38,7 +38,7 @@ The following options/arguments are optional:
38
38
-n, --namespace= Kubernetes namespace to create new server instance in. If not specified, server will be created in namespace "default".
39
39
-p, --cpu= Number of CPUs to reserve for Triton instance. Format: '0.5', '1', etc. If not specified, no CPUs will be reserved.
40
40
-b, --load-balancer Option to use a LoadBalancer instead of using NodePort service. If not specified, NodePort service will be utilized.
41
-
-r, --allocate-resource= Option to specify custom resource allocations. If not specified, no custom resource will be allocated.
41
+
-r, --allocate-resource= Option to specify custom resource allocations, ex. 'nvidia.com/mig-1g.5gb=1'. If not specified, no custom resource will be allocated.
42
42
```
43
43
44
44
##### Example Usage
@@ -163,7 +163,7 @@ def create_triton_server(
163
163
request_cpu: str=None, # Number of CPUs to reserve for Triton instance. Format: '0.5', '1', etc. If not specified, no CPUs will be reserved.
164
164
request_memory: str=None, # Amount of memory to reserve for Triton instance. Format: '1024Mi', '100Gi', '10Ti', etc. If not specified, no memory will be reserved.
165
165
request_nvidia_gpu: str=None, # Number of NVIDIA GPUs to allocate to Triton instance. Format: '1', '4', etc. If not specified, no GPUs will be allocated.
166
-
allocate_resource: str=None, # Option to specify custom resource allocations. If not specified, no custom resource will be allocated.
166
+
allocate_resource: str=None, # Option to specify custom resource allocations, ex. 'nvidia.com/mig-1g.5gb=1'. If not specified, no custom resource will be allocated.
167
167
print_output: bool=False# Denotes whether or not to print messages to the console during execution.
0 commit comments