Skip to content

Deferred GPU-resident sampling and pre-allocated decode tensors #779

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
mitiskuma wants to merge 1 commit into
base: main
Choose a base branch
from
+524 −217
Open

Deferred GPU-resident sampling and pre-allocated decode tensors #779

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
4 changes: 4 additions & 0 deletions src/engine.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,6 +455,7 @@ export class MLCEngine implements MLCEngineInterface {
}
await this.decode(pipeline, genConfig);
}
await pipeline.flushDeferredTokens?.(genConfig);
return pipeline.getMessage();
}

Expand Down Expand Up @@ -617,6 +618,9 @@ export class MLCEngine implements MLCEngineInterface {
}
}

// Flush any remaining deferred tokens
await pipeline.flushDeferredTokens?.(genConfig);

// Reset seed -- we do not want this seed to affect future requests
if (request.seed !== null && request.seed !== undefined) {
pipeline.setSeed(Date.now());
Expand Down
Loading
Loading