-
Notifications
You must be signed in to change notification settings - Fork 323
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
Upstreaming Groq changes #1703
Comments
That would be great! We already have a presentation for this Tu, would next week work? |
Yes next week would work well too |
Added on wiki meeting page. If you have a presentation deck, please add it here when available. |
Merged
We are making really good progress on this Only two PRs remaining: |
Actually there are two more after those But that is it! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
We have been working with
onnx-mlir
for years now at Groq. As a result we have added some additional features, bug fixes, and have some general divergence.Time permitting could we discuss a strategy for us upstreaming our changes in the
onnx-mlir
Tuesday meeting.Below is hopefully a comprehensive list of what we have
Add decompositions for v11 split, squeeze, and unsqueeze #1702
Topological sort implementation #1725
add MatMulInt shape inference #1761
Fix for GatherND verifier #1754
ingest float16 #1701
normalize axis in ScatterElements verify #1760
Lots of Constant Propagation (our implementation differs from the buffer implementation upstream)We ended up moving our divergent const prop into our codebase. And don't need this merged to delete our forkAdd more functionality to conv transpose shape inference #1771
Add shape inference for Upsample #1776
Add value info fix #1779
Derive kernel shape when not provided #1780
We see big benefits in minimizing our divergence from upstream. I'm actively working to upstream these changes. I want to make sure that we do it in a way that doesn't overwhelm.
The text was updated successfully, but these errors were encountered: