mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-29 04:35:05 +00:00
llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)
* llama : remove LLAMA_MAX_DEVICES from llama.h ggml-ci * Update llama.cpp Co-authored-by: slaren <slarengh@gmail.com> * server : remove LLAMA_MAX_DEVICES ggml-ci * llama : remove LLAMA_SUPPORTS_GPU_OFFLOAD ggml-ci * train : remove LLAMA_SUPPORTS_GPU_OFFLOAD * readme : add deprecation notice * readme : change deprecation notice to "remove" and fix url * llama : remove gpu includes from llama.h ggml-ci --------- Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
@ -88,7 +88,7 @@ int main(int argc, char ** argv) {
|
||||
|
||||
llama_model_params model_params = llama_model_default_params();
|
||||
|
||||
const std::vector<float> t_split (LLAMA_MAX_DEVICES, 0.0f);
|
||||
const std::vector<float> t_split(llama_max_devices(), 0.0f);
|
||||
|
||||
model_params.n_gpu_layers = n_gpu_layers;
|
||||
model_params.tensor_split = t_split.data();
|
||||
|
Reference in New Issue
Block a user