vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/full.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-intel.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-cli.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	CMakeLists.txt
#	CONTRIBUTING.md
#	Makefile
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	requirements.txt
#	src/llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-07-19 14:23:33 +08:00
commit 24b9616344
61 changed files with 12994 additions and 936 deletions
Download patch file Download diff file Expand all files Collapse all files

13
common/common.cpp
View file

@ -686,7 +686,6 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
if (arg == "--lora") {
CHECK_ARG
params.lora_adapter.emplace_back(argv[i], 1.0f);
params.use_mmap = false;
return true;
}
if (arg == "--lora-scaled") {
@ -694,7 +693,6 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
const char* lora_adapter = argv[i];
CHECK_ARG
params.lora_adapter.emplace_back(lora_adapter, std::stof(argv[i]));
params.use_mmap = false;
return true;
}
if (arg == "--lora-base") {
@ -2090,19 +2088,14 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
for (unsigned int i = 0; i < params.lora_adapter.size(); ++i) {
const std::string & lora_adapter = std::get<0>(params.lora_adapter[i]);
float lora_scale = std::get<1>(params.lora_adapter[i]);
int err = llama_model_apply_lora_from_file(model,
lora_adapter.c_str(),
lora_scale,
((i > 0) || params.lora_base.empty())
? NULL
: params.lora_base.c_str(),
params.n_threads);
if (err != 0) {
auto adapter = llama_lora_adapter_init(model, lora_adapter.c_str());
if (adapter == nullptr) {
fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
llama_free(lctx);
llama_free_model(model);
return std::make_tuple(nullptr, nullptr);
}
llama_lora_adapter_set(lctx, adapter, lora_scale);
}
if (params.ignore_eos) {