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/llama-server.Dockerfile
#	README.md
#	flake.lock
#	ggml/src/ggml-vulkan.cpp
#	ggml/src/vulkan-shaders/concat.comp
#	ggml/src/vulkan-shaders/pad.comp
#	ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-08-06 16:33:26 +08:00
commit e1f97f7fb5
55 changed files with 112612 additions and 111077 deletions
Download patch file Download diff file Expand all files Collapse all files

18
common/common.cpp
View file

@ -2040,8 +2040,8 @@ std::string fs_get_cache_file(const std::string & filename) {
//
// Model utils
//
std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_params(gpt_params & params) {
struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
llama_init_result iparams;
auto mparams = llama_model_params_from_gpt_params(params);
llama_model * model = nullptr;
@ -2056,7 +2056,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
if (model == NULL) {
fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
return std::make_tuple(nullptr, nullptr);
return iparams;
}
auto cparams = llama_context_params_from_gpt_params(params);
@ -2065,7 +2065,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
if (lctx == NULL) {
fprintf(stderr, "%s: error: failed to create context with model '%s'\n", __func__, params.model.c_str());
llama_free_model(model);
return std::make_tuple(nullptr, nullptr);
return iparams;
}
if (!params.control_vectors.empty()) {
@ -2076,7 +2076,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
if (cvec.n_embd == -1) {
llama_free(lctx);
llama_free_model(model);
return std::make_tuple(nullptr, nullptr);
return iparams;
}
int err = llama_control_vector_apply(lctx,
@ -2088,7 +2088,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
if (err) {
llama_free(lctx);
llama_free_model(model);
return std::make_tuple(nullptr, nullptr);
return iparams;
}
}
@ -2100,7 +2100,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
llama_free(lctx);
llama_free_model(model);
return std::make_tuple(nullptr, nullptr);
return iparams;
}
llama_lora_adapter_set(lctx, adapter, lora_scale);
}
@ -2136,7 +2136,9 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
llama_reset_timings(lctx);
}
return std::make_tuple(model, lctx);
iparams.model = model;
iparams.context = lctx;
return iparams;
}
struct llama_model_params llama_model_params_from_gpt_params(const gpt_params & params) {