-
Notifications
You must be signed in to change notification settings - Fork 1.4k
feat: Cache sin cos in model instead of global LRU cache. #3378
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
Conversation
/bot run --disable-fail-fast |
PR_Github #1496 [ run ] triggered by Bot |
PR_Github #1496 [ run ] completed with state |
/bot run --disable-fail-fast |
PR_Github #1527 [ run ] triggered by Bot |
PR_Github #1527 [ run ] completed with state |
30f7fb9
to
105c73b
Compare
/bot run --disable-fail-fast |
PR_Github #1746 [ run ] triggered by Bot |
PR_Github #1746 [ run ] completed with state |
/bot run --disable-fail-fast |
PR_Github #1896 [ run ] triggered by Bot |
/bot run --disable-fail-fast |
PR_Github #1943 [ run ] triggered by Bot |
PR_Github #1896 [ run ] completed with state |
PR_Github #1943 [ run ] completed with state |
5ce7c3a
to
b7f47ed
Compare
This PR is blocked by #3449 since the multi-gpu tests cannot pass without it. |
Signed-off-by: Yuxian Qiu <[email protected]>
b7f47ed
to
e0f4c56
Compare
/bot run --disable-fail-fast --stage-list "DGX_H100-4_GPUs-TensorRT-2" |
PR_Github #2013 [ run ] triggered by Bot |
PR_Github #2013 [ run ] completed with state |
/bot run --disable-fail-fast |
PR_Github #2015 [ run ] triggered by Bot |
PR_Github #2015 [ run ] completed with state |
/bot reuse-pipeline |
PR_Github #2093 [ reuse-pipeline ] triggered by Bot |
PR_Github #2093 [ reuse-pipeline ] completed with state |
/bot reuse-pipeline |
PR_Github #2098 [ reuse-pipeline ] triggered by Bot |
PR_Github #2098 [ reuse-pipeline ] completed with state |
/bot reuse-pipeline |
PR_Github #2102 [ reuse-pipeline ] triggered by Bot |
PR_Github #2102 [ reuse-pipeline ] completed with state |
No description provided.