llama : disable Direct IO by default (#19109)

* llama : disable Direct IO by default * cont : override mmap if supported
2026-01-28 09:11:13 +02:00
parent eef375ce16
commit c5c64f72ac
6 changed files with 10 additions and 13 deletions
@@ -545,7 +545,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
    }

    std::vector<std::string> splits = {};
-    llama_model_loader ml(fname_inp, splits, use_mmap, /*use_direct_io*/ true, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
+    llama_model_loader ml(fname_inp, splits, use_mmap, /*use_direct_io*/ false, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr);
    ml.init_mappings(false); // no prefetching

    llama_model model(llama_model_default_params());