Cache: add new flag to distinguish models that Cache but not static cache
#30800
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
gante
changed the title
_supports_cache_class to False, jamba has its own cache typeCache but not static cache
zucchini-nlp
approved these changes
May 14, 2024
ArthurZucker
approved these changes
May 15, 2024
4 tasks
|
@ArthurZucker we can remove this attribute when we update all Llama-copied models to support the static cache :D |
itazap
pushed a commit
that referenced
this pull request
May 24, 2024
… cache (#30800) * jamba cache * new flag * generate exception
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Outdated suggestions cannot be applied.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?
See title :)
Models like
Jamba(will only ever supportHybridMambaAttentionDynamicCache) orMistral(currently only supports dynamic caches, likeSinkCache) need a distinction in terms of support flags, to run the appropriate checks and tests.Without this flag, we have the following bad practices:
generate