Skip to content

Fix issue using count/min/max of inference-accelerators #414

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 24, 2025
Merged

Fix issue using count/min/max of inference-accelerators #414

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
02cc59b
Fix issue using count/min/max of inference-accelerators
dims Feb 22, 2025
fff385e
add int32 conversion on mismatch int filter
bwagner5 Feb 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions cmd/main.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,7 +174,7 @@ Full docs can be found at github.com/aws/amazon-` + binName
cli.ByteQuantityMinMaxRangeFlags(gpuMemoryTotal, nil, nil, "Number of GPUs' total memory (Example: 4 GiB)")
cli.StringFlag(gpuManufacturer, nil, nil, "GPU Manufacturer name (Example: NVIDIA)", nil)
cli.StringFlag(gpuModel, nil, nil, "GPU Model name (Example: K520)", nil)
cli.IntMinMaxRangeFlags(inferenceAccelerators, nil, nil, "Total Number of inference accelerators (Example: 4)")
cli.Int32MinMaxRangeFlags(inferenceAccelerators, nil, nil, "Total Number of inference accelerators (Example: 4)")
cli.StringFlag(inferenceAcceleratorManufacturer, nil, nil, "Inference Accelerator Manufacturer name (Example: AWS)", nil)
cli.StringFlag(inferenceAcceleratorModel, nil, nil, "Inference Accelerator Model name (Example: Inferentia)", nil)
cli.StringOptionsFlag(placementGroupStrategy, nil, nil, "Placement group strategy: [cluster, partition, spread]", []string{"cluster", "partition", "spread"})
Expand Down Expand Up @@ -387,7 +387,7 @@ Full docs can be found at github.com/aws/amazon-` + binName
GpuMemoryRange: cli.ByteQuantityRangeMe(flags[gpuMemoryTotal]),
GPUManufacturer: cli.StringMe(flags[gpuManufacturer]),
GPUModel: cli.StringMe(flags[gpuModel]),
InferenceAcceleratorsRange: cli.IntRangeMe(flags[inferenceAccelerators]),
InferenceAcceleratorsRange: cli.Int32RangeMe(flags[inferenceAccelerators]),
InferenceAcceleratorManufacturer: cli.StringMe(flags[inferenceAcceleratorManufacturer]),
InferenceAcceleratorModel: cli.StringMe(flags[inferenceAcceleratorModel]),
PlacementGroupStrategy: cli.StringMe(flags[placementGroupStrategy]),
Expand Down
8 changes: 8 additions & 0 deletions pkg/selector/selector.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -484,6 +484,14 @@ func exec(instanceType ec2types.InstanceType, filterName string, filter filterPa
if !isSupportedWithRangeInt64(iSpec, filter) {
return false, nil
}
case *int32:
var iSpec64 *int64
if iSpec != nil {
iSpec64 = aws.Int64(int64(*iSpec))
}
if !isSupportedWithRangeInt64(iSpec64, filter) {
return false, nil
}
case *int:
if !isSupportedWithRangeInt(iSpec, filter) {
return false, nil
Expand Down
2 changes: 1 addition & 1 deletion pkg/selector/types.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,7 +162,7 @@ type Filters struct {
GPUModel *string

// InferenceAcceleratorsRange filters inference accelerators available to the instance type
InferenceAcceleratorsRange *IntRangeFilter
InferenceAcceleratorsRange *Int32RangeFilter

// InferenceAcceleratorManufacturer filters by inference acceleartor manufacturer
InferenceAcceleratorManufacturer *string
Expand Down
Loading