-
Notifications
You must be signed in to change notification settings - Fork 152
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
fix(gpu): fix compression #1485
Conversation
63ffe07
to
b555014
Compare
b555014
to
207f689
Compare
9c18d2d
to
6f9337e
Compare
5bf3a50
to
8333a66
Compare
Now we can run compression benchmarks using the target |
e525fae
to
4611054
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey @pdroalves! Thanks a lot for this fix: I just have one question, just to check the additional argument bodies_count is necessary 🙂
backends/tfhe-cuda-backend/cuda/src/integer/compression/compression.cu
Outdated
Show resolved
Hide resolved
4611054
to
3d85789
Compare
3d85789
to
bc9d7a6
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We still have body on the c++ side vs bodies on the Rust side, but that's not really so much of an issue I'll merge it as it is I think.
Fixes some edge cases, including booleans and multi-gpu.
closes: https://github.com/zama-ai/tfhe-rs-internal/issues/686
PR content/description
Check-list: