diff --git a/packages/clients/src/api/inference/v1/marshalling.gen.ts b/packages/clients/src/api/inference/v1/marshalling.gen.ts index 4d838116e..c5fd9b12a 100644 --- a/packages/clients/src/api/inference/v1/marshalling.gen.ts +++ b/packages/clients/src/api/inference/v1/marshalling.gen.ts @@ -132,7 +132,6 @@ const unmarshalDeploymentQuantization = ( return { bits: data.bits, - enabled: data.enabled, } as DeploymentQuantization } @@ -279,7 +278,6 @@ const marshalDeploymentQuantization = ( defaults: DefaultValues, ): Record => ({ bits: request.bits, - enabled: request.enabled, }) const marshalEndpointSpec = ( diff --git a/packages/clients/src/api/inference/v1/types.gen.ts b/packages/clients/src/api/inference/v1/types.gen.ts index 400d80a7b..5177f5f0a 100644 --- a/packages/clients/src/api/inference/v1/types.gen.ts +++ b/packages/clients/src/api/inference/v1/types.gen.ts @@ -63,8 +63,6 @@ export interface ModelSupportedNode { } export interface DeploymentQuantization { - /** Whether to enable quantization for this deployment. */ - enabled: boolean /** * The number of bits each model parameter should be quantized to. The * quantization method is chosen based on this value.