[Bug fix] Register Fusion Pass fuse policy assign wrong output edges#514
Open
LeiWang1999 wants to merge 7 commits intomicrosoft:xboxfrom
Open
[Bug fix] Register Fusion Pass fuse policy assign wrong output edges#514LeiWang1999 wants to merge 7 commits intomicrosoft:xboxfrom
LeiWang1999 wants to merge 7 commits intomicrosoft:xboxfrom
Conversation
xiayuqing0622
approved these changes
Apr 12, 2023
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add Support for int16_t load ( bloom fp16 model
for Register fusion pass (welder) fused node with multiple outputs, current code makes a wrong assignment of output edge, which will cause mistakes in some cases.
3. re-write the CUDA_ARCH string in Cuda Codegen CMakeList.txt in a more friendly way.
in current way of
if we wanna use some features which must be in sm_86, we should comment the low cuda arch gencode flag, otherwise we will get an compilation error.
with the new CUDA_ARCH SET way
we no longer have this concern.
should be
grid[2].get_to(m_gridDim.z);