-
Notifications
You must be signed in to change notification settings - Fork 4.1k
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
Rearrange inference OPS and stop using builder.load #5490
Conversation
Hi @oelayan7 - thanks for the contribution, could you take a look at the failing tests? |
Kicked off a manual run of the |
This PR mainly handles all places where InferenceBuilder is used to access any op or a specific implementation for an op. Instead an op is defined, and its proper implementation is picked inside and the usage will be transparent to the user. What was done in the PR: 1) Added missing ops (added a py file with fallback mechanism) 2) Added missing fallback implementations for existing ops 3) removed all usages for builder.load and replaced them with ops instead. 4) a small change to softmax_context signature to fit the fallback signature.
@loadams Can you please trigger the CI (hopefully the last time :) ) |
@oelayan7 - I've got to push a fix for nv-accelerate tests, will get this merged shorlty. |
This PR mainly handles all places where InferenceBuilder is used to
access any op or a specific implementation for an op.
Instead an op is defined, and its proper implementation is picked inside
and the usage will be transparent to the user.
What was done in the PR: