Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Hi, Community! For The Test I Logged My New Model To Clearml-Server File Host And Take Models For Clearml-Serving From There. And It Works With Clearml-Serving Model Add, But For Clearml-Serving Model Auto-Update I Do Not Exactly Understand What Happens.

Hi, community! For the test I logged my new model to clearml-server file host and take models for clearml-serving from there. And it works with clearml-serving model add, but for clearml-serving model auto-update i do not exactly understand what happens. I see my auto-update model in models list in serving, but in output logs triton print that poll failed.

command for add model (which works)
clearml-serving --id 5e4851e9ec3f4f148e6bd21e68fe22c1 model add --engine triton --endpoint "test_model_pytorch_auto" --preprocess "examples/pytorch/preprocess.py" --name "test torch auto update v2" --project "serving test" --input-size 1 28 28 --input-name "INPUT__0" --input-type float32 --output-size -1 10 --output-name "OUTPUT__0" --output-type float32
command for model auto-update (which has some problems)
clearml-serving --id 5e4851e9ec3f4f148e6bd21e68fe22c1 model auto-update --engine triton --endpoint "test_model_pytorch_auto_v2" --preprocess "examples/pytorch/preprocess.py" --name "test torch auto update v2" --project "serving test" --input-size 1 28 28 --input-name "INPUT__0" --input-type float32 --output-size -1 10 --output-name "OUTPUT__0" --output_type float32

and in this command ( clearml-serving --id 5e4851e9ec3f4f148e6bd21e68fe22c1 model list ) output i see model which i added with model add in endpoints and can make requests and get responces
but the model which i added with model auto-update i see in Model Monitorings and can’t make requests on it
https://clearml.slack.com/files/U03NVCYSBV5/F03PB576KV4/image.png

  
  
Posted 2 years ago
Votes Newest

Answers


Hi AbruptHedgehog21
can you send the two models info page (i.e. the original and the updated one) ?
do you see the two endpoints ?
BTW: --version would add a version to the model (i.e. create a new endpoint with version "endpoint/{version}"

  
  
Posted 2 years ago