-
Notifications
You must be signed in to change notification settings - Fork 90
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
support GroupQueryAttention #676
base: main
Are you sure you want to change the base?
Conversation
atol=atol, | ||
equal_nan=True, | ||
), | ||
) | ||
|
||
class TestCudaOps(unittest.TestCase): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In the future (or potentially even in this PR), we can separate our Python tests for CUDA by different ops (like we do for cpu tests). Otherwise, in the long term this file will get too long (GitHub is already not showing its preview by default on this PR because of file size).
nit: regardless, we should probably rename this file as it is already under test/cuda
, so test_cudaops.py
is redundant.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could you add a C++ unit test for GroupQueryAttention as well under test/shared_test
?
…st_key nor past_value. Runtime CUDA error when copying result from GPU to CPU
support GroupQueryAttention