Skip to content

[performance] optimize tensor memory tracking loop #213

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

Open
ysdede wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[performance] optimize tensor memory tracking loop #213

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
10 changes: 3 additions & 7 deletions src/parakeet.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,15 +326,11 @@ export class ParakeetModel {
const logits = out['outputs'];
const outputState1 = out['output_states_1'];
const outputState2 = out['output_states_2'];
// [Perf] Tracking small collections via Array is ~4x faster than Set instantiation
const seenOutputs = [];
// [Perf] Skip known keys explicitly to avoid array tracking overhead
for (const key in out) {
if (!Object.hasOwn(out, key)) continue;
if (key === 'outputs' || key === 'output_states_1' || key === 'output_states_2' || !Object.hasOwn(out, key)) continue;
const value = out[key];
if (!value || typeof value.dispose !== 'function' || seenOutputs.includes(value)) continue;
seenOutputs.push(value);
if (value === logits || value === outputState1 || value === outputState2) continue;
value.dispose();
if (value?.dispose) value.dispose();
}
// Note: _targetTensor and _targetLenTensor are intentionally NOT disposed here.
// They wrap a shared Int32Array (_targetIdArray / _targetLenArray) that is mutated
Expand Down