File tree 6 files changed +48
-0
lines changed
scaleway/scaleway/inference/v1
scaleway-async/scaleway_async/inference/v1 6 files changed +48
-0
lines changed Original file line number Diff line number Diff line change @@ -311,6 +311,8 @@ async def update_deployment(
311
311
tags : Optional [List [str ]] = None ,
312
312
min_size : Optional [int ] = None ,
313
313
max_size : Optional [int ] = None ,
314
+ model_id : Optional [str ] = None ,
315
+ quantization : Optional [DeploymentQuantization ] = None ,
314
316
) -> Deployment :
315
317
"""
316
318
Update a deployment.
@@ -321,6 +323,8 @@ async def update_deployment(
321
323
:param tags: List of tags to apply to the deployment.
322
324
:param min_size: Defines the new minimum size of the pool.
323
325
:param max_size: Defines the new maximum size of the pool.
326
+ :param model_id: Id of the model to set to the deployment.
327
+ :param quantization: Quantization to use to the deployment.
324
328
:return: :class:`Deployment <Deployment>`
325
329
326
330
Usage:
@@ -347,6 +351,8 @@ async def update_deployment(
347
351
tags = tags ,
348
352
min_size = min_size ,
349
353
max_size = max_size ,
354
+ model_id = model_id ,
355
+ quantization = quantization ,
350
356
),
351
357
self .client ,
352
358
),
Original file line number Diff line number Diff line change @@ -639,6 +639,14 @@ def marshal_UpdateDeploymentRequest(
639
639
if request .max_size is not None :
640
640
output ["max_size" ] = request .max_size
641
641
642
+ if request .model_id is not None :
643
+ output ["model_id" ] = request .model_id
644
+
645
+ if request .quantization is not None :
646
+ output ["quantization" ] = marshal_DeploymentQuantization (
647
+ request .quantization , defaults
648
+ )
649
+
642
650
return output
643
651
644
652
Original file line number Diff line number Diff line change @@ -750,6 +750,16 @@ class UpdateDeploymentRequest:
750
750
Defines the new maximum size of the pool.
751
751
"""
752
752
753
+ model_id : Optional [str ]
754
+ """
755
+ Id of the model to set to the deployment.
756
+ """
757
+
758
+ quantization : Optional [DeploymentQuantization ]
759
+ """
760
+ Quantization to use to the deployment.
761
+ """
762
+
753
763
754
764
@dataclass
755
765
class UpdateEndpointRequest :
Original file line number Diff line number Diff line change @@ -309,6 +309,8 @@ def update_deployment(
309
309
tags : Optional [List [str ]] = None ,
310
310
min_size : Optional [int ] = None ,
311
311
max_size : Optional [int ] = None ,
312
+ model_id : Optional [str ] = None ,
313
+ quantization : Optional [DeploymentQuantization ] = None ,
312
314
) -> Deployment :
313
315
"""
314
316
Update a deployment.
@@ -319,6 +321,8 @@ def update_deployment(
319
321
:param tags: List of tags to apply to the deployment.
320
322
:param min_size: Defines the new minimum size of the pool.
321
323
:param max_size: Defines the new maximum size of the pool.
324
+ :param model_id: Id of the model to set to the deployment.
325
+ :param quantization: Quantization to use to the deployment.
322
326
:return: :class:`Deployment <Deployment>`
323
327
324
328
Usage:
@@ -345,6 +349,8 @@ def update_deployment(
345
349
tags = tags ,
346
350
min_size = min_size ,
347
351
max_size = max_size ,
352
+ model_id = model_id ,
353
+ quantization = quantization ,
348
354
),
349
355
self .client ,
350
356
),
Original file line number Diff line number Diff line change @@ -639,6 +639,14 @@ def marshal_UpdateDeploymentRequest(
639
639
if request .max_size is not None :
640
640
output ["max_size" ] = request .max_size
641
641
642
+ if request .model_id is not None :
643
+ output ["model_id" ] = request .model_id
644
+
645
+ if request .quantization is not None :
646
+ output ["quantization" ] = marshal_DeploymentQuantization (
647
+ request .quantization , defaults
648
+ )
649
+
642
650
return output
643
651
644
652
Original file line number Diff line number Diff line change @@ -750,6 +750,16 @@ class UpdateDeploymentRequest:
750
750
Defines the new maximum size of the pool.
751
751
"""
752
752
753
+ model_id : Optional [str ]
754
+ """
755
+ Id of the model to set to the deployment.
756
+ """
757
+
758
+ quantization : Optional [DeploymentQuantization ]
759
+ """
760
+ Quantization to use to the deployment.
761
+ """
762
+
753
763
754
764
@dataclass
755
765
class UpdateEndpointRequest :
You can’t perform that action at this time.
0 commit comments