Skip to content

Commit

Permalink
Update inference_rules.adoc
Browse files Browse the repository at this point in the history
  • Loading branch information
arjunsuresh authored Dec 3, 2024
1 parent 84690f6 commit f400723
Showing 1 changed file with 1 addition and 3 deletions.
4 changes: 1 addition & 3 deletions inference_rules.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -757,9 +757,7 @@ The following techniques are disallowed:
downsampling inputs and kernels for the first convolution.

* Techniques that only improve performance when there are identical
samples in a query. For example, sorting samples in SSD.

* Techniques that reduce the number of unique samples in a query. For example, sorting samples in Graph Neural Networks' RGAT.
samples in a query. For example, sorting samples in SSD and R-GAT.

* Speculative decoding for auto-generative language models (i.e. using a smaller model to predict the next token for the reference model).

Expand Down

0 comments on commit f400723

Please sign in to comment.