Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	common/common.cpp
#	ggml/CMakeLists.txt
#	scripts/sync-ggml.last
#	scripts/sync_vendor.py
#	src/llama-context.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-17 11:26:18 +08:00
parent 9d38a9edc0 0253fb21f5
commit 1e828ccabf
66 changed files with 2205 additions and 504 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.cpp
+10 -3
View File
@@ -1313,9 +1313,16 @@ struct ggml_tensor * llama_model_loader::create_tensor_as_view(struct ggml_conte
return tensor;
}
void llama_model_loader::done_getting_tensors() const {
if (n_created != n_tensors) {
throw std::runtime_error(format("%s: wrong number of tensors; expected %d, got %d", __func__, n_tensors, n_created));
void llama_model_loader::done_getting_tensors(bool partial) const {
if (n_created > n_tensors) {
throw std::runtime_error(format("%s: too many tensors created; expected %d, got %d", __func__, n_tensors, n_created));
}
if (n_created < n_tensors) {
if (!partial) {
throw std::runtime_error(format("%s: wrong number of tensors; expected %d, got %d", __func__, n_tensors, n_created));
}
LLAMA_LOG_INFO("%s: partial load — used %d of %d tensors in the file (rest belong to a sibling model on the same .gguf)\n",
__func__, n_created, n_tensors);
}
if (n_tensors_moved > 0) {
LLAMA_LOG_DEBUG("%s: tensor '%s' (%s) (and %zu others) moved from %s, using %s instead\n",