Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[QST] Does CUTLASS 3.5.1 support int4 x float16 GEMMs natively? #1928

Open
SimpleTheoryOfTypes opened this issue Nov 7, 2024 · 3 comments
Open

[QST] Does CUTLASS 3.5.1 support int4 x float16 GEMMs natively? #1928

SimpleTheoryOfTypes opened this issue Nov 7, 2024 · 3 comments
Labels
? - Needs Triage question Question

Comments

@SimpleTheoryOfTypes
Copy link

SimpleTheoryOfTypes commented Nov 7, 2024 •
edited
Loading

What is your question?
By "natively," I mean without relying on third-party implementations. If I understand correctly, FasterTransformer and TVM have already developed their own CUTLASS extensions for constructing INT4/INT8 x FLOAT16 GEMMs. Just wondering if the latest CUTLASS release can already do this now? Thanks!
@thakkarV
Copy link
Collaborator

thakkarV commented Nov 8, 2024

see example 55

@SimpleTheoryOfTypes
Copy link
Author

SimpleTheoryOfTypes commented Nov 8, 2024 •
edited
Loading

see example 55

Thank you so much! sorry, I forgot to mention that my question is about int4 x fp16 GEMMs on Ampere, not Hopper. :).

@thakkarV
Copy link
Collaborator

thakkarV commented Nov 8, 2024

#1084

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
? - Needs Triage question Question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@thakkarV @SimpleTheoryOfTypes