ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-04-16 07:26:56 +00:00
Code Issues Actions 18 Packages Projects Releases Wiki Activity

chore(deps): bump llama.cpp to 'f01bd02376f919b05ee635f438311be8dfc91d7c (#5110)

Browse Source 
chore(deps): bump llama.cpp to 'f01bd02376f919b05ee635f438311be8dfc91d7c'

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-03 10:23:14 +02:00 committed by GitHub
parent 89e151f035
commit 18b320d577
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -6,7 +6,7 @@ BINARY_NAME=local-ai
DETECT_LIBS?=true
# llama.cpp versions
CPPLLAMA_VERSION?=f423981ac806bf031d83784bcb47d2721bc70f97
CPPLLAMA_VERSION?=f01bd02376f919b05ee635f438311be8dfc91d7c
# whisper.cpp version
WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp

16
backend/cpp/llama/grpc-server.cpp
View File

@ -509,15 +509,15 @@ struct llama_server_context
bool load_model(const common_params &params_)
{
params = params_;
if (!params.mmproj.empty()) {
if (!params.mmproj.path.empty()) {
multimodal = true;
LOG_INFO("Multi Modal Mode Enabled", {});
clp_ctx = clip_init(params.mmproj.c_str(), clip_context_params {
clp_ctx = clip_init(params.mmproj.path.c_str(), clip_context_params {
/* use_gpu */ has_gpu,
/*verbosity=*/ 1,
});
if(clp_ctx == nullptr) {
LOG_ERR("unable to load clip model: %s", params.mmproj.c_str());
LOG_ERR("unable to load clip model: %s", params.mmproj.path.c_str());
return false;
}
@ -531,7 +531,7 @@ struct llama_server_context
ctx = common_init.context.release();
if (model == nullptr)
{
LOG_ERR("unable to load model: %s", params.model.c_str());
LOG_ERR("unable to load model: %s", params.model.path.c_str());
return false;
}
@ -2326,11 +2326,11 @@ static void params_parse(const backend::ModelOptions* request,
// this is comparable to: https://github.com/ggerganov/llama.cpp/blob/d9b33fe95bd257b36c84ee5769cc048230067d6f/examples/server/server.cpp#L1809
params.model = request->modelfile();
params.model.path = request->modelfile();
if (!request->mmproj().empty()) {
// get the directory of modelfile
std::string model_dir = params.model.substr(0, params.model.find_last_of("/\\"));
params.mmproj = model_dir + "/"+ request->mmproj();
std::string model_dir = params.model.path.substr(0, params.model.path.find_last_of("/\\"));
params.mmproj.path = model_dir + "/"+ request->mmproj();
}
// params.model_alias ??
params.model_alias = request->modelfile();
@ -2405,7 +2405,7 @@ static void params_parse(const backend::ModelOptions* request,
scale_factor = request->lorascale();
}
// get the directory of modelfile
std::string model_dir = params.model.substr(0, params.model.find_last_of("/\\"));
std::string model_dir = params.model.path.substr(0, params.model.path.find_last_of("/\\"));
params.lora_adapters.push_back({ model_dir + "/"+request->loraadapter(), scale_factor });
}
params.use_mlock = request->mlock();