vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-09 19:46:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/docker.yml
#	README.md
#	build-xcframework.sh
#	examples/llava/CMakeLists.txt
#	examples/llava/clip.cpp
#	examples/rpc/rpc-server.cpp
#	examples/run/run.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
This commit is contained in:
Concedo 2025-04-12 10:06:47 +08:00
commit a0ae187563
33 changed files with 2247 additions and 1202 deletions
Download patch file Download diff file Expand all files Collapse all files

19
common/common.cpp
View file

@ -837,7 +837,7 @@ std::string fs_get_cache_directory() {
if (getenv("LLAMA_CACHE")) {
cache_directory = std::getenv("LLAMA_CACHE");
} else {
#ifdef __linux__
#if defined(__linux__) || defined(__FreeBSD__)
if (std::getenv("XDG_CACHE_HOME")) {
cache_directory = std::getenv("XDG_CACHE_HOME");
} else {
@ -847,7 +847,9 @@ std::string fs_get_cache_directory() {
cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
#elif defined(_WIN32)
cache_directory = std::getenv("LOCALAPPDATA");
#endif // __linux__
#else
# error Unknown architecture
#endif
cache_directory = ensure_trailing_slash(cache_directory);
cache_directory += "llama.cpp";
}
@ -1034,6 +1036,19 @@ struct common_init_result common_init_from_params(common_params & params) {
return iparams;
}
std::string get_model_endpoint() {
const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
// We still respect the use of environment-variable "HF_ENDPOINT" for backward-compatibility.
const char * hf_endpoint_env = getenv("HF_ENDPOINT");
const char * endpoint_env = model_endpoint_env ? model_endpoint_env : hf_endpoint_env;
std::string model_endpoint = "https://huggingface.co/";
if (endpoint_env) {
model_endpoint = endpoint_env;
if (model_endpoint.back() != '/') model_endpoint += '/';
}
return model_endpoint;
}
void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora) {
llama_clear_adapter_lora(ctx);
for (auto & la : lora) {