-
Notifications
You must be signed in to change notification settings - Fork 175
feat(gpu): add support for a custom device selection on multi-gpu mode #2245
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
base: main
Are you sure you want to change the base?
Conversation
3ba3139
to
46e4f39
Compare
@@ -341,10 +342,10 @@ impl Named for CompressedServerKey { | |||
} | |||
|
|||
#[cfg(feature = "gpu")] | |||
#[derive(Clone)] |
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.
Keep the derive
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.
The custom case in the CudaStreamPools is not able to handle all possible cases but for now it should be enough
dede9e5
to
78b8a44
Compare
// let gpus_to_be_used = (0..num_gpus).map(|i| { | ||
// let gpu_idx = rng.gen_range(0..get_number_of_gpus()); | ||
// GpuIndex::new(gpu_idx) | ||
// }).collect_vec(); |
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.
remove
… a custom selection of GPUs
78b8a44
to
90b119c
Compare
closes: https://github.com/zama-ai/tfhe-rs-internal/issues/960
PR content/description
Check-list: