Accumulate tokens in generate mode #1534
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1534
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit facb0b7 with merge base 359db61 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Jack-Khuu
approved these changes
Apr 22, 2025
| @@ -294,6 +295,7 @@ def from_args(cls, args): | |||
| sequential_prefill=sequential_prefill, | |||
| max_autotune=args.max_autotune, | |||
| is_torchtune_model=args.model and args.model.endswith("tune"), | |||
| accumulate_tokens=getattr(args, "accumulate_tokens", 8), | |||
There was a problem hiding this comment.
Unrelated to this PR: I should fix this so we don't have duplicate defaults
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
We accumulate tokens in generate mode before calling callback on them.
This avoids synchronizing GPU and CPU on each token, improving performance on MPS backend.