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

fix: Pass backend in BatchPrefillWith*KVCacheWrapper.plan() #808

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

sfc-gh-yewang
Copy link

@sfc-gh-yewang sfc-gh-yewang commented Feb 12, 2025

Fix #807

For the BatchPrefillWith*KVCacheWrapper that support both FA2 and FA3, user may call the ctor() once and the plan() multiple times.

This PR adds support to reset/select backend in plan()

@sfc-gh-yewang sfc-gh-yewang changed the title Pass backend in BatchPrefillWith*KVCacheWrapper.plan() fix: Pass backend in BatchPrefillWith*KVCacheWrapper.plan() Feb 12, 2025
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.

BatchPrefillWithPagedKVCacheSM90Run failed with error: operation not supported
1 participant