☝️ Update Jetstream Pytorch revision #91
Merged
Conversation
This file contains 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
Now that decode takes a specialized method this is not necessary anymore.
Now that sampling can be passed as parameter to prefill and generate, the custom engine is not required anymore.
mfuntowicz
approved these changes
Sep 12, 2024
Comment on lines
486
to
487
| active_slots = [slot for slot in self.slots if slot.state == slot.State.READY] | ||
| for slot in active_slots: |
There was a problem hiding this comment.
Maybe we can avoid the double iteration by filtering on the fly through the main iteration?
Suggested change
| active_slots = [slot for slot in self.slots if slot.state == slot.State.READY] | |
| for slot in active_slots: | |
| for slot in filter(lambda slot: slot.state == slot.State.READY, slots): |
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Outdated suggestions cannot be applied.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.
What does this PR do?
This is a refactoring PR. It updates the Jetstream/Pytorch version to a newer revision, that allows to pass the sampler function as parameter to the
prefillandgeneratefunctions, as we requested. This simplifies our code, making theHfEngineusage redundant, so we can drop it.