github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-03 09:34:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

expose n_gpu_layers parameter of llama.cpp (#1890)

Browse Source 
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-01-31 14:17:44 -05:00
committed by GitHub
parent f549d5a70a
commit 061d1969f8
31 changed files with 381 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
gpt4all-bindings/typescript/index.cc
View File

@@ -28,7 +28,7 @@ Napi::Function NodeModelWrapper::GetClass(Napi::Env env) {
Napi::Value NodeModelWrapper::GetRequiredMemory(const Napi::CallbackInfo& info)
{
auto env = info.Env();
return Napi::Number::New(env, static_cast<uint32_t>( llmodel_required_mem(GetInference(), full_model_path.c_str(), 2048) ));
return Napi::Number::New(env, static_cast<uint32_t>( llmodel_required_mem(GetInference(), full_model_path.c_str(), 2048, 100) ));
}
Napi::Value NodeModelWrapper::GetGpuDevices(const Napi::CallbackInfo& info)
@@ -161,7 +161,7 @@ Napi::Value NodeModelWrapper::GetRequiredMemory(const Napi::CallbackInfo& info)
}
}
auto success = llmodel_loadModel(GetInference(), full_weight_path.c_str(), 2048);
auto success = llmodel_loadModel(GetInference(), full_weight_path.c_str(), 2048, 100);
if(!success) {
Napi::Error::New(env, "Failed to load model at given path").ThrowAsJavaScriptException();
return;