是的，AWS Sagemaker支持gRPC的预测请求。您可以使用AWS Sagemaker SDK for Python来创建gRPC请求。以下是一个使用gRPC进行预测的示例代码：

import boto3
import numpy as np
import sagemaker as sage
from sagemaker.tensorflow.serving import Model

runtime = boto3.Session().client("sagemaker-runtime")

model = Model(
    model_data="s3://bucket-name/path/to/model.tar.gz",
    role="arn:aws:iam::123456789012:role/ExecutionRole-XXX",
    framework_version="2.1.0",
)

predictor = model.deploy(initial_instance_count=1, instance_type="ml.m4.xlarge", endpoint_name="grpc-endpoint")

request_data = np.array([1.0, 2.0, 3.0])
response = runtime.invoke_endpoint(
    EndpointName="grpc-endpoint",
    ContentType="application/grpc",
    Body=request_data.tobytes(),
)

print(response)