Skip to content

Commit 8847916

Browse files
scaleway-botyfodil
andauthored
feat(inference): update max_size field documentation (#5463)
Co-authored-by: Yacine Fodil <105779815+yfodil@users.noreply.github.com>
1 parent ac34f27 commit 8847916

File tree

4 files changed

+6
-6
lines changed

4 files changed

+6
-6
lines changed

cmd/scw/testdata/test-all-usage-inference-deployment-create-usage.golden

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ ARGS:
1313
node-type-name Name of the node type to use
1414
[tags.{index}] List of tags to apply to the deployment
1515
[min-size] Defines the minimum size of the pool
16-
[max-size] Defines the maximum size of the pool
16+
[max-size] Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to `min_size`
1717
[endpoints.{index}.is-public=true] Will configure your public endpoint if true
1818
[endpoints.{index}.private-network.private-network-id]
1919
[endpoints.{index}.disable-auth=false] Disable the authentication on the endpoint.

cmd/scw/testdata/test-all-usage-inference-deployment-update-usage.golden

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ ARGS:
1010
[name] Name of the deployment
1111
[tags.{index}] List of tags to apply to the deployment
1212
[min-size] Defines the new minimum size of the pool
13-
[max-size] Defines the new maximum size of the pool
13+
[max-size] Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to `min_size`
1414
[model-id] Id of the model to set to the deployment
1515
[quantization.bits] The number of bits each model parameter should be quantized to. The quantization method is chosen based on this value.
1616
[region=fr-par] Region to target. If none is passed will use default region from the config (fr-par)

docs/commands/inference.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -49,7 +49,7 @@ scw inference deployment create [arg=value ...]
4949
| node-type-name | Required | Name of the node type to use |
5050
| tags.{index} | | List of tags to apply to the deployment |
5151
| min-size | | Defines the minimum size of the pool |
52-
| max-size | | Defines the maximum size of the pool |
52+
| max-size | | Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to `min_size` |
5353
| endpoints.{index}.is-public | Default: `true` | Will configure your public endpoint if true |
5454
| endpoints.{index}.private-network.private-network-id | | |
5555
| endpoints.{index}.disable-auth | Default: `false` | Disable the authentication on the endpoint. |
@@ -162,7 +162,7 @@ scw inference deployment update <deployment-id ...> [arg=value ...]
162162
| name | | Name of the deployment |
163163
| tags.{index} | | List of tags to apply to the deployment |
164164
| min-size | | Defines the new minimum size of the pool |
165-
| max-size | | Defines the new maximum size of the pool |
165+
| max-size | | Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to `min_size` |
166166
| model-id | | Id of the model to set to the deployment |
167167
| quantization.bits | | The number of bits each model parameter should be quantized to. The quantization method is chosen based on this value. |
168168
| region | Default: `fr-par`<br />One of: `fr-par` | Region to target. If none is passed will use default region from the config |

internal/namespaces/inference/v1/inference_cli.go

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -247,7 +247,7 @@ func inferenceDeploymentCreate() *core.Command {
247247
},
248248
{
249249
Name: "max-size",
250-
Short: `Defines the maximum size of the pool`,
250+
Short: `Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to ` + "`" + `min_size` + "`" + ``,
251251
Required: false,
252252
Deprecated: false,
253253
Positional: false,
@@ -326,7 +326,7 @@ func inferenceDeploymentUpdate() *core.Command {
326326
},
327327
{
328328
Name: "max-size",
329-
Short: `Defines the new maximum size of the pool`,
329+
Short: `Defines the maximum size of the pool. Currently, autoscaling is not yet supported, and this value must be equal to ` + "`" + `min_size` + "`" + ``,
330330
Required: false,
331331
Deprecated: false,
332332
Positional: false,

0 commit comments

Comments
 (0)