chore: ⬆️ Update leejet/stable-diffusion.cpp to d8fb10c02977c8ca999f3fb4e02df9ecf10f7ba6 (#11898)

* ⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(stablediffusion): adapt streaming options

Upstream now selects segmented weight streaming automatically and removes the stream_layers field. Keep the old LocalAI option as a no-op for existing model configurations.

Assisted-by: Codex:gpt-5

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=6b3edaaf32cc19e5bb2d819c788bd557eddc8eba
+STABLEDIFFUSION_GGML_VERSION?=d8fb10c02977c8ca999f3fb4e02df9ecf10f7ba6
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/stablediffusion-ggml/cpp/gosd.cpp

@@ -401,7 +401,6 @@ int load_model(const char *model, char *model_path, char* options[], int threads
     const char *params_backend_arg = "";
     const char *rpc_servers_arg = "";
     const char *max_vram_arg = "";
-    bool stream_layers = false;
 
     int n_threads = threads;
     enum sd_type_t wtype = SD_TYPE_COUNT;
@@ -510,7 +509,10 @@ int load_model(const char *model, char *model_path, char* options[], int threads
         if (!strcmp(optname, "params_backend")) params_backend_arg = strdup(optval);
         if (!strcmp(optname, "rpc_servers")) rpc_servers_arg = strdup(optval);
         if (!strcmp(optname, "max_vram")) max_vram_arg = strdup(optval);
-        if (!strcmp(optname, "stream_layers")) stream_layers = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
+        if (!strcmp(optname, "stream_layers")) {
+            // Retained as a no-op for existing configurations. Upstream now
+            // selects segmented weight streaming automatically.
+        }
 
         // vae_decode_only is still accepted for backwards compatibility with
         // existing gallery configs, but upstream dropped the option (the model
@@ -650,11 +652,9 @@ int load_model(const char *model, char *model_path, char* options[], int threads
             ctx_params.rpc_servers = env_rpc_servers;
         }
     }
-    // max_vram: GiB budget or per-backend spec for graph-cut segmented param
-    // offload ("0" = disabled, "-1" = auto). stream_layers only has effect when
-    // max_vram is set.
+    // max_vram is an optional GiB budget or per-backend spec for automatic
+    // graph-cut execution. A zero value uses the live free-VRAM budget.
     if (strlen(max_vram_arg) > 0) ctx_params.max_vram = max_vram_arg;
-    ctx_params.stream_layers = stream_layers;
     ctx_params.diffusion_flash_attn = diffusion_flash_attn;
     ctx_params.tae_preview_only = tae_preview_only;
     ctx_params.diffusion_conv_direct = diffusion_conv_direct;
@@ -1438,4 +1438,3 @@ int unload() {
     free_sd_ctx(sd_c);
     return 0;
 }
-

docs/content/features/image-generation.md

@@ -79,8 +79,8 @@ When a model does not fit entirely in VRAM, the following `options:` control whe
 |--------|---------|-------------|
 | `backend` | `backend:clip=cpu,vae=cuda0,diffusion=vulkan0` | Runtime (compute) backend assignment per component. Use `cpu` to place a component's compute on the CPU. Component keys include `te` (text encoder / CLIP), `vae`, `diffusion`, `controlnet`. |
 | `params_backend` | `params_backend:diffusion=disk,clip=cpu` | Where parameters (weights) are stored. Supports `cpu`, `disk` (mmap weights from disk to save RAM/VRAM), or per-component specs. |
-| `max_vram` | `max_vram:8` or `max_vram:-1` | VRAM budget (in GiB) for graph-cut segmented parameter offload. `0` disables it, `-1` auto-selects (free VRAM minus ~1 GiB). Also accepts per-backend budgets. |
-| `stream_layers` | `stream_layers:true` | Enable residency + prefetch streaming on top of `max_vram` (no effect unless `max_vram` is set). |
+| `max_vram` | `max_vram:8` or `max_vram:-1` | Optional per-device VRAM budget (in GiB) for managed weights and automatic graph-cut execution. `0` uses live free VRAM without an explicit cap; a negative value reserves that many GiB of free VRAM. Also accepts per-backend budgets. |
+| `stream_layers` | `stream_layers:true` | Deprecated compatibility option. Segmented weight streaming is now selected automatically, so this value is ignored. |
 | `rpc_servers` | `rpc_servers:localhost:50052,192.168.1.3:50052` | Comma-separated list of `host:port` RPC servers to offload compute to. |
 | `pulid_weights_path` | `pulid_weights_path:pulid.safetensors` | Path to PuLID-Flux weights for identity injection. |