custom triton cache manager #3659

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

Closed

grimoire wants to merge 5 commits into InternLM:main from grimoire:custom-triton-cache-manager

Collaborator

grimoire commented Jun 20, 2025 •

edited

Loading

enable by LMDEPLOY_TRITON_CUSTOM_CACHE_MGR_ENABLE=1 (disable by default)
Compiled kernel would be shared by all tp rank
remove unused code

grimoire added 5 commits

June 20, 2025 15:53


          custom triton cache manager

5f6ce82


          use old annotation

efce129


          triton cache manager

cf5b574


          remove unused kernel/keys

709646b


          merge main

76527ca

grimoire closed this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet