vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-04-28 03:30:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit '01d8eaa28d' into concedo_experimental

Browse source 
# Conflicts:
#	build-xcframework.sh
#	scripts/sync_vendor.py
#	tests/test-backend-ops.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/rpc/rpc-server.cpp
This commit is contained in:
Concedo 2026-02-16 15:36:59 +08:00
commit 72f7e01b27
102 changed files with 1655 additions and 3247 deletions
Download patch file Download diff file Expand all files Collapse all files

21
include/llama.h
View file

@ -659,21 +659,12 @@ extern "C" {
// The following functions operate on a llama_context, hence the naming: llama_verb_...
// Add a loaded LoRA adapter to given context
// This will not modify model's weight
LLAMA_API int32_t llama_set_adapter_lora(
// Set LoRa adapters on the context. Will only modify if the adapters currently in context are different.
LLAMA_API int32_t llama_set_adapters_lora(
struct llama_context * ctx,
struct llama_adapter_lora * adapter,
float scale);
// Remove a specific LoRA adapter from given context
// Return -1 if the adapter is not present in the context
LLAMA_API int32_t llama_rm_adapter_lora(
struct llama_context * ctx,
struct llama_adapter_lora * adapter);
// Remove all LoRA adapters from given context
LLAMA_API void llama_clear_adapter_lora(struct llama_context * ctx);
struct llama_adapter_lora ** adapters,
size_t n_adapters,
float * scales);
// Apply a loaded control vector to a llama_context, or if data is NULL, clear
// the currently loaded vector.
@ -681,7 +672,7 @@ extern "C" {
// to an n_embd x n_layers buffer starting from layer 1.
// il_start and il_end are the layer range the vector should apply to (both inclusive)
// See llama_control_vector_load in common to load a control vector.
LLAMA_API int32_t llama_apply_adapter_cvec(
LLAMA_API int32_t llama_set_adapter_cvec(
struct llama_context * ctx,
const float * data,
size_t len,