Skip to content

Commit 2c4f51b

Browse files
committed
build: Remove 0003-embeddings.patch
The embedding logic was overhauled in ggml-org/llama.cpp#14208 to support embeddings with causal attention and logits + embeddings output Branch: GraniteFour Signed-off-by: Gabe Goodhart <[email protected]>
1 parent 65bff66 commit 2c4f51b

File tree

1 file changed

+0
-43
lines changed

1 file changed

+0
-43
lines changed

llama/patches/0003-embeddings.patch

Lines changed: 0 additions & 43 deletions
This file was deleted.

0 commit comments

Comments
 (0)