Skip to content

Commit

Permalink
[ML] fixing bwc for trained model deployment inference (#88289) (#88315)
Browse files Browse the repository at this point in the history
When the internal objects were renamed, an inappropriate bwc version restriction was put in place.

This commit fixes this by allowing trained model assignment metadata updates to be serialized to nodes > 8.0.0.

This is OK as the object serialization handles its BWC conditions when serializing over the wire.

This closes: #87959
  • Loading branch information
benwtrent committed Jul 8, 2022
1 parent dc31d03 commit 031a174
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 4 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ public String getWriteableName() {

@Override
public Version getMinimalSupportedVersion() {
return Version.V_8_3_0;
return Version.V_8_0_0;
}

@Override
Expand Down Expand Up @@ -265,7 +265,7 @@ public String getWriteableName() {

@Override
public Version getMinimalSupportedVersion() {
return Version.V_8_3_0;
return Version.V_8_0_0;
}

@Override
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -79,8 +79,10 @@ public void testTrainedModelDeployment() throws Exception {
request.addParameter("timeout", "70s");
}));
waitForDeploymentStarted(modelId);
assertInfer(modelId);
assertInfer(modelId);
// attempt inference on new and old nodes multiple times
for (int i = 0; i < 10; i++) {
assertInfer(modelId);
}
}
case UPGRADED -> {
ensureHealth(".ml-inference-*,.ml-config*", (request -> {
Expand Down

0 comments on commit 031a174

Please sign in to comment.