configuration file for a MME in aws sagemaker?

0

based on the example here ,

https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-triton/ensemble/sentence-transformer-trt/examples/ensemble_hf/ensemble/config.pbtxt, i am working on a configuration file for a multi model endpoint on a bert based model. which takes on a string and outputs a string. the max_batch_size and the dims:[1] parameters below are not very clear . Is there any more info on this . triton server documentation is not very clear as well, from what i saw.

name: "ensemble"
platform: "ensemble"
max_batch_size: 16
input [
  {
    name: "INPUT0"
    data_type: TYPE_STRING
    dims: [ 1 ]
  }
]
output [
  {
    name: "finaloutput"
    data_type: TYPE_FP32
    dims: [384]
  }
]

已提问 10 个月前69 查看次数
没有答案

您未登录。 登录 发布回答。

一个好的回答可以清楚地解答问题和提供建设性反馈,并能促进提问者的职业发展。

回答问题的准则