feat: auto fit tensors across devices to guarantee optimal load (#1736)

This commit is contained in:
Piotr Wilkin (ilintar) authored and GitHub committed 2026-07-05 00:48:10 +08:00
1 parent 68f3d6df9f
commit b11c95a41c
8 files changed
+493 -16

No files matched your search

+1
View File
@@ -152,6 +152,7 @@ struct SDContextParams {
std::string backend;
std::string params_backend;
std::string split_mode;
bool auto_fit = false;
std::string rpc_servers;
std::string effective_backend;
std::string effective_params_backend;