Skip to content

Support latest kernels created in vllm, move old kernels to legacy #24

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

Merged
merged 10 commits into from
Jun 24, 2025

Conversation

bringlein
Copy link
Collaborator

@bringlein bringlein commented Jun 19, 2025

  • update build processes (bare metal and docker) to latest version
    • cuda
    • rocm
  • move old kernels to legacy
  • add new vllm kernels
  • ensure support of prefix prefill benchmark v1
  • verify correctness

if we keep the "legacy" stuff can be discussed...I thought maybe we keep it for the moment so that we can compare to them as baseline if necessary.

Signed-off-by: Burkhard Ringlein <[email protected]>
Signed-off-by: Burkhard Ringlein <[email protected]>
Signed-off-by: Burkhard Ringlein <[email protected]>
Signed-off-by: Burkhard Ringlein <[email protected]>
…ck/vllm-triton-backend into ngl_cleanup_2025-06
Signed-off-by: Burkhard Ringlein <[email protected]>
Co-authored-by: [email protected]
Co-authored-by: [email protected]
Signed-off-by: Burkhard Ringlein <[email protected]>
Signed-off-by: Burkhard Ringlein <[email protected]>
@bringlein bringlein requested review from tdoublep and jvlunteren June 19, 2025 13:50
Signed-off-by: Burkhard Ringlein <[email protected]>
Copy link
Collaborator

@jvlunteren jvlunteren left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@bringlein bringlein merged commit 37e650c into main Jun 24, 2025
1 check passed
@bringlein bringlein deleted the ngl_cleanup_2025-06 branch June 24, 2025 16:20
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