This repository was archived by the owner on Sep 10, 2025. It is now read-only.
native runner: convert logits to float #1198
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/1198
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit fce0c79 with merge base f343b43 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced Sep 24, 2024
swolchok
requested review from
Jack-Khuu,
JacobSzwejbka and
mergennachin
and removed request for
mergennachin
larryliu0820
approved these changes
Sep 24, 2024
| .to(torch::dtype(torch::kFloat32)) | ||
| .to(torch::kCPU); | ||
| auto logits = result[0].data_ptr(); | ||
| memcpy(s->logits, logits, p->vocab_size * sizeof(float)); |
There was a problem hiding this comment.
This is for AOTI right? This is needed because the rest of the runner assumes float?
There was a problem hiding this comment.
it is simply moved up from below.
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
The native runner incorrectly assumed that the output of the model
must always be float. Now it doesn't.