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

fix: dynamic temperature scaling in multi-node inference #544

Draft

AlpinDale wants to merge 2 commits into rc_054 from multinode_dynatemp

Member

AlpinDale commented Jul 23, 2024

Seems like our current implementation has an issue:

                    dynatemp_logits = logits[dynatemp_mask]
ERROR:        |                       ~~~~~~^^^^^^^^^^^^^^^
ERROR:        | IndexError: The shape of the mask [1] at index 0 does not match the shape of the indexed tensor [0, 128256] at index 0


          potential fix

cbfc7f9

AlpinDale changed the base branch from main to rc_054

July 23, 2024 09:00


          formatting

c2be1b9

AlpinDale requested a review from sgsdxzy

July 23, 2024 10:11

AlpinDale marked this pull request as draft

July 23, 2024 10:24

AlpinDale mentioned this pull request

fix: sampler indexing issues in distributed environments #546

Merged

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet