Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-06 21:11:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	src/CMakeLists.txt
This commit is contained in:
Concedo
2026-02-16 23:02:03 +08:00
parent b6becb9ad4 2ba9adc093
commit e469c9f934
21 changed files with 502 additions and 452 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+10 -8
View File
@@ -25,6 +25,8 @@ llama_context::llama_context(
const llama_model & model,
llama_context_params params) :
model(model),
cvec(std::make_unique<llama_adapter_cvec>()),
loras(std::make_unique<llama_adapter_loras>()),
balloc(std::make_unique<llama_batch_allocr>(model.hparams.n_pos_per_embd())) {
// TODO warning when creating llama_context with awkward ctx size that is not a power of 2,
// may need to be backend-dependent
@@ -1075,11 +1077,11 @@ void llama_context::set_adapters_lora(llama_adapter_lora ** adapters, size_t n_a
return;
}
loras.clear();
loras.reset(new llama_adapter_loras());
for (size_t i = 0; i < n_adapters; i ++) {
if (scales[i] != 0.0f) {
loras[adapters[i]] = scales[i];
loras->insert({adapters[i], scales[i]});
}
}
@@ -1089,14 +1091,14 @@ void llama_context::set_adapters_lora(llama_adapter_lora ** adapters, size_t n_a
bool llama_context::adapters_lora_are_same(llama_adapter_lora ** adapters, size_t n_adapters, float * scales) {
LLAMA_LOG_DEBUG("%s: adapters = %p\n", __func__, (void *) adapters);
if (n_adapters != loras.size()) {
if (n_adapters != loras->size()) {
return false;
}
for (size_t i = 0; i < n_adapters; i ++) {
auto it = loras.find(adapters[i]);
auto it = loras->find(adapters[i]);
if (it == loras.end() || it->second != scales[i]) {
if (it == loras->end() || it->second != scales[i]) {
return false;
}
}
@@ -1114,7 +1116,7 @@ bool llama_context::set_adapter_cvec(
// TODO: should we reserve?
return cvec.apply(model, data, len, n_embd, il_start, il_end);
return cvec->apply(model, data, len, n_embd, il_start, il_end);
}
llm_graph_result * llama_context::process_ubatch(const llama_ubatch & ubatch, llm_graph_type gtype, llama_memory_context_i * mctx, ggml_status & ret) {
@@ -2091,8 +2093,8 @@ llm_graph_params llama_context::graph_params(
/*.gtype =*/ gtype,
/*.sched =*/ sched.get(),
/*.backend_cpu =*/ backend_cpu,
/*.cvec =*/ &cvec,
/*.loras =*/ &loras,
/*.cvec =*/ cvec.get(),
/*.loras =*/ loras.get(),
/*.mctx =*/ mctx,
/*.cross =*/ &cross,
/*.samplers =*/ sampling.samplers,