Fix bugs and typos in source code. #14
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The wmma is not supported for fp32/fp64. Cutlass also does not support either but I convert them to fp16/bf16 in the kernel. Also, cutlass kernel can only run multiple of 16 channels or configurations allowed by engine cutlass engine so more restrictive. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Found some bugs and typos in the source code found during running the tests.
algo=
wmma_implicit_gemmfailed on A100 with pytorch 2.4.1 and cuda 12.1.algo=
cutlass_implicit_gemmreturns -1 during benchmarking.therefore, only explicit and implicit works on my side.
PS: the test code seems to be not up to date. Could you please have a look and maybe update it according the latest source code?