feat(inference): remove DeploymentQuantization.enabled field (#922)

Co-authored-by: Jonathan R. <jremy@scaleway.com>

Author: scaleway-bot

scaleway-async/scaleway_async/inference/v1/marshalling.py

@@ -167,10 +167,6 @@ def unmarshal_DeploymentQuantization(data: Any) -> DeploymentQuantization:
 
     args: Dict[str, Any] = {}
 
-    field = data.get("enabled", None)
-    if field is not None:
-        args["enabled"] = field
-
     field = data.get("bits", None)
     if field is not None:
         args["bits"] = field
@@ -497,9 +493,6 @@ def marshal_DeploymentQuantization(
 ) -> Dict[str, Any]:
     output: Dict[str, Any] = {}
 
-    if request.enabled is not None:
-        output["enabled"] = request.enabled
-
     if request.bits is not None:
         output["bits"] = request.bits
 

scaleway-async/scaleway_async/inference/v1/types.py

@@ -113,11 +113,6 @@ class ModelSupportedNode:
 
 @dataclass
 class DeploymentQuantization:
-    enabled: bool
-    """
-    Whether to enable quantization for this deployment.
-    """
-
     bits: int
     """
     The number of bits each model parameter should be quantized to. The quantization method is chosen based on this value.

scaleway/scaleway/inference/v1/marshalling.py

@@ -167,10 +167,6 @@ def unmarshal_DeploymentQuantization(data: Any) -> DeploymentQuantization:
 
     args: Dict[str, Any] = {}
 
-    field = data.get("enabled", None)
-    if field is not None:
-        args["enabled"] = field
-
     field = data.get("bits", None)
     if field is not None:
         args["bits"] = field
@@ -497,9 +493,6 @@ def marshal_DeploymentQuantization(
 ) -> Dict[str, Any]:
     output: Dict[str, Any] = {}
 
-    if request.enabled is not None:
-        output["enabled"] = request.enabled
-
     if request.bits is not None:
         output["bits"] = request.bits
 

scaleway/scaleway/inference/v1/types.py

@@ -113,11 +113,6 @@ class ModelSupportedNode:
 
 @dataclass
 class DeploymentQuantization:
-    enabled: bool
-    """
-    Whether to enable quantization for this deployment.
-    """
-
     bits: int
     """
     The number of bits each model parameter should be quantized to. The quantization method is chosen based on this value.