vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : move CPU backend to a separate file (#10144)

Browse source
This commit is contained in:
Diego Devesa 2024-11-03 19:34:08 +01:00 • committed by GitHub
parent 08828a6d7d
commit 9f40989351
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
32 changed files with 14747 additions and 19345 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/llava/clip.cpp
View file

@ -4,6 +4,7 @@
// Note: Even when using identical normalized image inputs (see normalize_image_u8_to_f32()) we have a significant difference in resulting embeddings compared to pytorch
#include "clip.h"
#include "ggml.h"
#include "ggml-cpu.h"
#include "ggml-alloc.h"
#include "ggml-backend.h"