Skip to content

Remove smaller limit for legacy bfloat16 serialization#505

Draft
borzunov wants to merge 1 commit into
mainfrom
payload-size
Draft

Remove smaller limit for legacy bfloat16 serialization#505
borzunov wants to merge 1 commit into
mainfrom
payload-size

Conversation

@borzunov

@borzunov borzunov commented Sep 5, 2023

Copy link
Copy Markdown
Collaborator

Revert #251 since it's not needed after #311. This may improve fine-tuning efficiency for medium-sized batches.

TODO:

  • Test it with increasingly larger batches. Watch that we switch from rpc_forward to rpc_forward_stream (can be distinguished using server logs) without errors.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant