tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-26 11:13:53 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : remove ggml_cplan + rework ggml_cgraph

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-09-11 13:05:10 +03:00
parent ee154457dd
commit 119e0bc9ae
10 changed files with 248 additions and 175 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/llava/llava.cpp
View File

@ -183,7 +183,9 @@ 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_graph_prepare(gf, 1, nullptr);
ggml_graph_work_init(gf, model.ctx);
ggml_graph_compute(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