LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

fit : count nextn (MTP) blocks in n_gpu_layers so front layers stay on GPU (#26177)

Browse Source
This commit is contained in:
Jonas Jankaitis
2026-07-27 16:21:37 +03:00
committed by GitHub
parent 8e8681e0e2
commit 0324696b8e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/fit.cpp
+1 -1
View File
@@ -136,7 +136,7 @@ static std::vector<llama_device_memory_data> common_get_device_memory_data_impl(
devs.push_back(llama_model_get_device(model, i));
}
hp_ngl = llama_model_n_layer(model);
hp_ngl = llama_model_n_layer(model) + llama_model_n_layer_nextn(model);
hp_n_ctx_train = llama_model_n_ctx_train(model);
hp_n_expert = llama_model_n_expert(model);