Skip to content

Allow backends to auto-complete model transaction policy #283

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 2, 2023
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion src/backend_model.cc
Original file line number Diff line number Diff line change
Expand Up @@ -693,7 +693,6 @@ TritonModel::UpdateModelConfig(
JsonToModelConfig({buffer, byte_size}, config_version, &updated_config));
auto config = Config();
config.set_max_batch_size(updated_config.max_batch_size());

auto inputs_config = config.mutable_input();
*inputs_config = updated_config.input();
auto outputs_config = config.mutable_output();
Expand Down Expand Up @@ -722,6 +721,12 @@ TritonModel::UpdateModelConfig(
.c_str());
} // else do nothing

// Update model_transaction_policy if needed
if (updated_config.has_model_transaction_policy()) {
bool is_decoupled = updated_config.model_transaction_policy().decoupled();
config.mutable_model_transaction_policy()->set_decoupled(is_decoupled);
}

// Need to normalize the model configuration for
// populating missing fields.
RETURN_IF_ERROR(NormalizeModelConfig(min_compute_capability_, &config));
Expand Down