vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 02:19:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '5215b91e93' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	cmake/x64-windows-llvm.cmake
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/CMakeLists.txt
#	tools/imatrix/imatrix.cpp
#	tools/llava/clip.cpp
#	tools/rpc/rpc-server.cpp
This commit is contained in:
Concedo 2025-05-06 23:15:04 +08:00
commit 1377a93a73
21 changed files with 1183 additions and 467 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tools/llava/llava.cpp
View file

@ -2,6 +2,7 @@
#include "llava.h"
#include "llama.h"
#include "ggml-cpp.h"
#include <algorithm>
#include <cerrno>
@ -209,7 +210,10 @@ static bool clip_llava_handle_patches(clip_ctx * ctx_clip, std::vector<float *>
struct ggml_tensor *flatten = ggml_view_2d(model.ctx, permuted_cont, clip_n_mmproj_embd(ctx_clip), num_patches_height * num_patches_width * num_patches_per_side * num_patches_per_side, size_ele * clip_n_mmproj_embd(ctx_clip), 0);
// ggml_tensor_printf(flatten,"flatten",__LINE__,false,false);
ggml_build_forward_expand(gf, flatten);
ggml_graph_compute_with_ctx(model.ctx, gf, 1);
ggml_backend_ptr backend { ggml_backend_init_by_type(GGML_BACKEND_DEVICE_TYPE_CPU, nullptr) };
ggml_backend_graph_compute(backend.get(), gf);
struct ggml_tensor* result = ggml_graph_node(gf, -1);
memcpy(image_embd_out, image_embd_v[0], clip_embd_nbytes(ctx_clip)); // main image as global context