Add portable CPU longhaul support
This commit is contained in:
+1
-1
@@ -2631,7 +2631,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
).set_env("LLAMA_ARG_LOAD_MODE"));
|
||||
add_opt(common_arg(
|
||||
{"--longhaul"},
|
||||
"stream routed Qwen3.5 MoE experts through a bounded Metal cache",
|
||||
"stream routed Qwen3.5 MoE or Laguna experts through a bounded CPU or Metal cache",
|
||||
[](common_params & params) {
|
||||
params.load_mode = LLAMA_LOAD_MODE_LONGHAUL;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user