Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

common: migrate the deprecated --mmap/--no-mmap to --load-mode (#26934)

Browse Source 
Replace the deprecated --mmap, --no-mmap, --mlock, and --direct-io flags with
the unified --load-mode argument across scripts, examples, and documentation.
Internal warning message and env var docs updated accordingly.

Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org>
This commit is contained in:
Fathi Boudra
2026-08-15 16:35:53 +08:00
committed by GitHub
parent 6b4344ecc7
commit 0177dcc730
21 changed files with 48 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.cpp
+1 -1
View File
@@ -1178,7 +1178,7 @@ struct ggml_tensor * llama_model_loader::create_tensor(
if (use_mmap) {
static std::once_flag once;
std::call_once(once, [] {
LLAMA_LOG_WARN("llama_model_loader: tensor overrides to CPU are used with mmap enabled - consider using --no-mmap for better performance\n");
LLAMA_LOG_WARN("llama_model_loader: tensor overrides to CPU are used with mmap enabled - consider using --load-mode none for better performance\n");
});
}
} else {