Add portable CPU longhaul support

This commit is contained in:
Owen Qwen
2026-07-30 16:59:40 -05:00
parent a673afad85
commit d5458aa44e
11 changed files with 277 additions and 23 deletions
+1 -1
View File
@@ -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;
}