text-generation-inference
Tied embeddings in MLP speculator.
#2473
Merged

Tied embeddings in MLP speculator. #2473

Narsil merged 3 commits into main from upgrade_mlp_speculator2
Narsil
OlivierDehaene
OlivierDehaene commented on 2024-08-29
Narsil Tied embeddings in MLP speculator.
62a83431
Narsil Fixing the scale_weight when users decide to not use the speculation as
09a1de5c
Narsil Adding scaling support + optimize some ops.
9f036684
Narsil Narsil force pushed from 8cef03f6 to 9f036684 1 year ago
OlivierDehaene
OlivierDehaene approved these changes on 2024-08-29
Narsil Narsil merged d9fbbaaf into main 1 year ago
Narsil Narsil deleted the upgrade_mlp_speculator2 branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone