Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-04 03:51:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '5a69c974392020e514c3b2b2910bb92f847cb4c9' into concedo_experimental

Browse Source 
# Conflicts:
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/concat.cl
#	ggml/src/ggml-opencl/kernels/cpy.cl
#	ggml/src/ggml-opencl/kernels/get_rows.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_q6_k_f32_flat.cl
#	tests/test-chat.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/clip.cpp
#	tools/mtmd/clip.h
This commit is contained in:
Concedo
2026-06-07 17:46:09 +08:00
parent 202aaef40b 5a69c97439
commit e40e5c660e
30 changed files with 1301 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-graph.cpp
+6 -1
View File
@@ -1859,7 +1859,12 @@ ggml_tensor * llm_graph_context::build_inp_embd(ggml_tensor * tok_embd) const {
res->t_inp_embd = cur;
// For Granite architecture
if (hparams.f_embedding_scale != 0.0f) {
// NOTE: Only apply scale to token inputs. Raw embeddings are assumed to be
// multimodal inputs that should not be scaled.
if (ubatch.token && hparams.f_embedding_scale != 0.0f) {
if (!ggml_is_contiguous(cur)) {
cur = ggml_cont(ctx0, cur);
}
cur = ggml_scale(ctx0, cur, hparams.f_embedding_scale);
}