Skip to content

LLM inference in C/C++

C++ ggml

Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR not implemented for architecture' message (#24926)

kdkde3546c7948e3
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 7dea38c87d..d87481381e 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -313,8 +313,7 @@ llama_model * llama_model_create(llm_arch arch, const llama_model_params & param
if (model != nullptr) {
model->arch = arch;
- auto & devices = model->devices;
- if (!devices.empty() && devices[0].is_meta && !llm_arch_supports_sm_tensor(arch)) {
+ if (params.split_mode == LLAMA_SPLIT_MODE_TENSOR && !llm_arch_supports_sm_tensor(arch)) {
throw std::runtime_error(std::string("LLAMA_SPLIT_MODE_TENSOR not implemented for architecture '") + llm_arch_name(arch) + "'");
}
}