feat: support backend-specific max-vram budgets

This commit is contained in:
leejet
2026-06-14 22:46:32 +08:00
parent 517abc777d
commit bb90bfa00f
9 changed files with 223 additions and 39 deletions

View File

@@ -216,7 +216,7 @@ typedef struct {
int chroma_t5_mask_pad;
bool qwen_image_zero_cond_t;
enum sd_vae_format_t vae_format;
float max_vram; // GiB budget for graph-cut segmented param offload (0 = disabled, -1 = auto free VRAM minus 1 GiB)
const char* max_vram; // GiB budget or backend assignment spec for graph-cut segmented param offload (0 = disabled, -1 = auto)
bool stream_layers; // Enable residency+prefetch streaming on top of --max-vram (no effect without --max-vram)
const char* backend;
const char* params_backend;