vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	examples/embedding/embedding.cpp
#	tools/imatrix/imatrix.cpp
#	tools/perplexity/perplexity.cpp
This commit is contained in:
Concedo 2025-05-08 23:41:02 +08:00
commit 2439014a03
40 changed files with 2058 additions and 429 deletions
Download patch file Download diff file Expand all files Collapse all files

12
src/llama-model.cpp
View file

@ -1666,8 +1666,11 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
for (const auto * overrides = ml.tensor_buft_overrides; overrides->pattern != nullptr; ++overrides) {
std::regex pattern(overrides->pattern);
if (std::regex_search(tensor_name, pattern)) {
LLAMA_LOG_DEBUG("tensor %s buffer type overriden to %s\n", tensor_name.c_str(), ggml_backend_buft_name(overrides->buft));
buft = overrides->buft;
LLAMA_LOG_DEBUG("tensor %s (%zu MiB %s) buffer type overridden to %s\n",
tensor_name.c_str(),
ggml_nbytes(t_meta) / 1024 / 1024, ggml_type_name(t_meta->type),
ggml_backend_buft_name(buft));
break;
}
}
@ -12952,6 +12955,13 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
llama_memory_i * res;
switch (arch) {
case LLM_ARCH_BERT:
case LLM_ARCH_JINA_BERT_V2:
case LLM_ARCH_NOMIC_BERT:
case LLM_ARCH_NOMIC_BERT_MOE:
{
res = nullptr;
} break;
case LLM_ARCH_MAMBA:
case LLM_ARCH_RWKV6:
case LLM_ARCH_RWKV6QWEN2: