Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-03 11:35:48 +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-context.cpp
+2 -2
View File
@@ -344,7 +344,7 @@ llama_context::llama_context(
// enabling pipeline parallelism in the scheduler increases memory usage, so it is only done when necessary
bool pipeline_parallel =
model.n_devices() > 1 &&
model.n_gpu_layers() > model.hparams.n_layer() &&
model.n_gpu_layers() > model.hparams.n_layer_all &&
model.split_mode() == LLAMA_SPLIT_MODE_LAYER &&
cparams.offload_kqv &&
!model.has_tensor_overrides();
@@ -2361,7 +2361,7 @@ llm_graph_cb llama_context::graph_get_cb() const {
// norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends
// FIXME: fix in ggml_backend_sched
const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer();
const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer_all;
if (ubatch.n_tokens < 32 || full_offload) {
if (il != -1 && strcmp(name, "norm") == 0) {
const auto & dev_layer = model.dev_layer(il);