Skip to content
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.

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

[RWKV] Follow-up to fix cache management #168

Merged
merged 6 commits into from
Feb 6, 2025

Conversation

jannalulu
Copy link
Contributor

@jannalulu jannalulu commented Feb 5, 2025

*added the fixes that I made to rwkv7 to rwkv6

*add check in legacy cache

(cont. implement @SmerkyG's suggestions in issue #157--they are all implemented now)

@yzhangcs
Copy link
Member

yzhangcs commented Feb 6, 2025

@jannalulu Hey, could you split this PR into 2 parts? one for code formats and one for RWKV cache.

@yzhangcs yzhangcs merged commit 79d1b61 into fla-org:main Feb 6, 2025
1 check passed
@jannalulu jannalulu deleted the fix-fla-generation branch February 6, 2025 19:20
rucnyz pushed a commit to rucnyz/flash-linear-attention that referenced this pull request Feb 8, 2025
* fix bug in state tracking

* check whether past_key_values are empty

* fix linting errors

* missed some fixes for rwkv6

* add check in legacy_cache
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants