feat: support for cross-device row split (#1735)

This commit is contained in:
Piotr Wilkin (ilintar) authored and GitHub committed 2026-07-04 16:31:18 +08:00
1 parent 7bcd189639
commit 68f3d6df9f
12 files changed
+322 -21

No files matched your search

+1
View File
@@ -227,6 +227,7 @@ typedef struct {
bool eager_load; // Load all params into the params backend at model-load time instead of lazily on first use
const char* backend;
const char* params_backend;
const char* split_mode; // weight distribution for multi-device modules: layer (default) or row, or per-module assignments e.g. "diffusion=row"
const char* rpc_servers;
} sd_ctx_params_t;