diff --git a/src/llama-model.cpp b/src/llama-model.cpp index 72639b155..dbc91a137 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -1697,8 +1697,8 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) { } } - // resolve AUTO on systems without mmap support (e.g. iGPUs): fall back to OFF; see #28160 - if (ml.lazy.mode == LLAMA_LAZY_MODE_AUTO) { + // resolve AUTO on systems without mmap support (e.g. iGPUs): fall back to OFF unless mmap is in use; see #28160, #31943 + if (ml.lazy.mode == LLAMA_LAZY_MODE_AUTO && !ml.use_mmap) { for (const auto & dev : devices) { ggml_backend_dev_props props; ggml_backend_dev_get_props(dev.dev, &props);