Skip to content

Runner logs #15279

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.

Sign up for GitHub

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 1 commit into from
Oct 21, 2025
Merged

Runner logs #15279

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 5 additions & 4 deletions extension/llm/runner/text_llm_runner.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,6 +169,11 @@ Error TextLLMRunner::generate(
stats_->first_token_ms = time_in_ms();
stats_->prompt_eval_end_ms = time_in_ms();

RUNNER_ET_LOG(
config.warming,
"RSS after prompt prefill: %f MiB (0 if unsupported)",
get_rss_bytes() / 1024.0 / 1024.0);

// print the first token from prefill. No prev_token so use cur_token for it.
auto decode_result = tokenizer_->decode(cur_token, cur_token);
if (!decode_result.ok()) {
Expand All @@ -179,10 +184,6 @@ Error TextLLMRunner::generate(
return ::executorch::runtime::Error::InvalidArgument;
}
wrapped_callback(std::move(*decode_result));
RUNNER_ET_LOG(
config.warming,
"RSS after prompt prefill: %f MiB (0 if unsupported)",
get_rss_bytes() / 1024.0 / 1024.0);

// start the main loop
prompt_tokens.push_back(cur_token);
Expand Down
6 changes: 5 additions & 1 deletion extension/llm/runner/text_token_generator.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,9 +128,13 @@ class ET_EXPERIMENTAL TextTokenGenerator {
if (eos_ids_->find(cur_token) != eos_ids_->end()) {
printf("\n");
Copy link
Contributor

@JacobSzwejbka JacobSzwejbka Oct 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

not your change but weird we have a printf

ET_LOG(Info, "\nReached to the end of generation");
break;
return pos - start_pos;
Copy link
Contributor

@JacobSzwejbka JacobSzwejbka Oct 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you put this in a variable and share it

Copy link
Contributor

@JacobSzwejbka JacobSzwejbka Oct 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh its in the loop. Nvm I guess

Copy link
Contributor Author

@lucylq lucylq Oct 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Leaving as-is, because one is inside a while loop and another is not.

}
}
ET_LOG(
Info,
"\nFinished generation. Generated %" PRIi32 " tokens.",
start_pos + max_new_tokens);
return pos - start_pos;
}

Expand Down
Loading