Skip to content

Conversation

@jeffbolznv
Copy link
Collaborator

Split out from #10206.

Original goal was to be able to use multiple quant formats in the same shader. I ended up not actually doing that in #10206, but maybe in the future. Also, after #10409 you do need to define DATA_A_IQ4_NL to use iq4_nl. I'm sure it's fixable, but not for today.

Should be no functional change.

@jeffbolznv jeffbolznv requested a review from 0cc4m November 20, 2024 20:22
@0cc4m 0cc4m merged commit c31ed2a into ggml-org:master Nov 27, 2024
7 checks passed
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Dec 20, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants