vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 16:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build-cross.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	examples/llama.android/lib/src/main/cpp/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync_vendor.py
#	tests/test-chat.cpp
#	tests/test-mtmd-c-api.c
#	tools/server/README.md
This commit is contained in:
Concedo 2026-04-20 20:19:11 +08:00
commit cd6788007e
86 changed files with 1384 additions and 1240 deletions
Download patch file Download diff file Expand all files Collapse all files

18
src/llama-graph.cpp
View file

@ -1077,9 +1077,9 @@ llm_graph_qkv llm_graph_context::build_qkv(
// fused QKV path
ggml_tensor * qkv = build_lora_mm(layer.wqkv, cur, layer.wqkv_s);
cb(qkv, "wqkv", il);
if (layer.bqkv) {
qkv = ggml_add(ctx0, qkv, layer.bqkv);
cb(qkv, "bqkv", il);
if (layer.wqkv_b) {
qkv = ggml_add(ctx0, qkv, layer.wqkv_b);
cb(qkv, "wqkv_b", il);
}
if (hparams.f_clamp_kqv > 0.0f) {
qkv = ggml_clamp(ctx0, qkv, -hparams.f_clamp_kqv, hparams.f_clamp_kqv);
@ -1097,8 +1097,8 @@ llm_graph_qkv llm_graph_context::build_qkv(
// separate Q/K/V path
Qcur = build_lora_mm(layer.wq, cur, layer.wq_s);
cb(Qcur, "Qcur", il);
if (layer.bq) {
Qcur = ggml_add(ctx0, Qcur, layer.bq);
if (layer.wq_b) {
Qcur = ggml_add(ctx0, Qcur, layer.wq_b);
cb(Qcur, "Qcur", il);
}
if (hparams.f_clamp_kqv > 0.0f) {
@ -1107,8 +1107,8 @@ llm_graph_qkv llm_graph_context::build_qkv(
}
Kcur = build_lora_mm(layer.wk, cur, layer.wk_s);
cb(Kcur, "Kcur", il);
if (layer.bk) {
Kcur = ggml_add(ctx0, Kcur, layer.bk);
if (layer.wk_b) {
Kcur = ggml_add(ctx0, Kcur, layer.wk_b);
cb(Kcur, "Kcur", il);
}
if (hparams.f_clamp_kqv > 0.0f) {
@ -1117,8 +1117,8 @@ llm_graph_qkv llm_graph_context::build_qkv(
}
Vcur = build_lora_mm(layer.wv, cur, layer.wv_s);
cb(Vcur, "Vcur", il);
if (layer.bv) {
Vcur = ggml_add(ctx0, Vcur, layer.bv);
if (layer.wv_b) {
Vcur = ggml_add(ctx0, Vcur, layer.wv_b);
cb(Vcur, "Vcur", il);
}
if (hparams.f_clamp_kqv > 0.0f) {