Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-28 16:10:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '6effcecd0bf3cb2209999cecfa297ed4d8523b5a' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-msys.yml
#	.pi/gg/SYSTEM.md
#	common/CMakeLists.txt
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	scripts/ui-assets.cmake
#	src/llama-model.cpp
#	tools/cli/cli.cpp
#	tools/imatrix/imatrix.cpp
#	tools/quantize/quantize.cpp
#	tools/server/README.md
#	tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-06-07 17:10:58 +08:00
parent 5f39666705 6effcecd0b
commit 202aaef40b
152 changed files with 1188 additions and 878 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+2 -2
View File
@@ -849,7 +849,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<t
qs.has_tied_embeddings = false;
}
}
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer;
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer();
}
//
@@ -1350,7 +1350,7 @@ llama_model * llama_quant_model_from_metadata(const llama_quant_model_desc * des
model->hparams.n_embd = desc->n_embd;
model->hparams.n_embd_head_k_full = desc->n_embd_head_k;
model->hparams.n_embd_head_v_full = desc->n_embd_head_v;
model->hparams.n_layer = desc->n_layer;
model->hparams.n_layer_all = desc->n_layer;
model->hparams.n_expert = desc->n_expert;
for (uint32_t i = 0; i < desc->n_layer; i++) {