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.

Sign up for GitHub

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

Jump to bottom

Fix illegal memory access in overlap mode & Use more fused triton kernels for building meta data #2051

Merged
merged 2 commits into from
Nov 17, 2024
Merged

Fix illegal memory access in overlap mode & Use more fused triton kernels for building meta data #2051

merged 2 commits into from
Nov 17, 2024
+198 −83

Conversation

merrymercy
Copy link
Contributor

@merrymercy merrymercy commented Nov 16, 2024 •
edited
Loading

  • Fix illegal memory access in overlap model by introducing a synchronization
  • Implement some fused triton kernels for building the metadata of prefill
  • Simplify copy queue in overlap model

@merrymercy merrymercy changed the title Simplify copy queue Fix illegal memory access in overlap mode & Use more fused triton kernels for building meta data Nov 16, 2024
@merrymercy merrymercy merged commit edad373 into main Nov 17, 2024
13 checks passed
@merrymercy merrymercy deleted the pr-fix-overlap branch November 17, 2024 00:14
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Ying1123 Ying1123 Awaiting requested review from Ying1123 Ying1123 is a code owner

@hnyls2002 hnyls2002 Awaiting requested review from hnyls2002 hnyls2002 is a code owner

@zhyncs zhyncs Awaiting requested review from zhyncs zhyncs is a code owner

@ispobock ispobock Awaiting requested review from ispobock ispobock is a code owner

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@merrymercy