feat(stablediffusion-ggml): build a ROCm variant (#11774)

The Makefile already had a hipblas branch, but no CI row built it and
the gallery's `amd:` mapping stayed commented out. On an AMD host the
capability lookup found no `amd` key and fell back to `default`, so
these users silently ran the CPU build.

Add the hipblas row to the backend matrix and the two gallery entries
it publishes, then point `amd:` at them.

Drop `-DGGML_HIPBLAS=ON` while here. `SD_HIPBLAS` sets `GGML_HIP`
itself, and `GGML_HIPBLAS` is the name ggml used before the rename, so
the flag only produced an unused-variable warning. Add gfx1151 to the
local target list to match the value the workflows pass in.


Assisted-by: Claude Code:claude-opus-5[1m]

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>

.github/backend-matrix.yml

@@ -3754,6 +3754,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-stablediffusion-ggml'
+    runs-on: 'ubuntu-latest'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    skip-drivers: 'false'
+    backend: "stablediffusion-ggml"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f16'
     cuda-major-version: ""
     cuda-minor-version: ""

backend/go/stablediffusion-ggml/Makefile

@@ -38,8 +38,11 @@ else ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_PATH ?= /opt/rocm
 	export CXX=$(ROCM_HOME)/llvm/bin/clang++
 	export CC=$(ROCM_HOME)/llvm/bin/clang
-	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
-	CMAKE_ARGS+=-DSD_HIPBLAS=ON -DGGML_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
+	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
+	# SD_HIPBLAS turns on ggml's HIP backend itself; GGML_HIPBLAS is the name ggml
+	# used before it was renamed to GGML_HIP, so passing it here only produced an
+	# unused-variable warning.
+	CMAKE_ARGS+=-DSD_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
 else ifeq ($(BUILD_TYPE),vulkan)
 	CMAKE_ARGS+=-DSD_VULKAN=ON -DGGML_VULKAN=ON
 else ifeq ($(BUILD_TYPE),metal)

backend/index.yaml

@@ -510,7 +510,7 @@
     default: "cpu-stablediffusion-ggml"
     nvidia: "cuda12-stablediffusion-ggml"
     intel: "intel-sycl-f16-stablediffusion-ggml"
-    # amd: "rocm-stablediffusion-ggml"
+    amd: "rocm-stablediffusion-ggml"
     vulkan: "vulkan-stablediffusion-ggml"
     nvidia-l4t: "nvidia-l4t-arm64-stablediffusion-ggml"
     metal: "metal-stablediffusion-ggml"
@@ -2109,7 +2109,7 @@
     default: "cpu-stablediffusion-ggml-development"
     nvidia: "cuda12-stablediffusion-ggml-development"
     intel: "intel-sycl-f16-stablediffusion-ggml-development"
-    # amd: "rocm-stablediffusion-ggml-development"
+    amd: "rocm-stablediffusion-ggml-development"
     vulkan: "vulkan-stablediffusion-ggml-development"
     nvidia-l4t: "nvidia-l4t-arm64-stablediffusion-ggml-development"
     metal: "metal-stablediffusion-ggml-development"
@@ -3904,6 +3904,11 @@
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml"
   mirrors:
     - localai/localai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml
+- !!merge <<: *stablediffusionggml
+  name: "rocm-stablediffusion-ggml"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-stablediffusion-ggml"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-stablediffusion-ggml
 - !!merge <<: *stablediffusionggml
   name: "intel-sycl-f32-stablediffusion-ggml"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-stablediffusion-ggml"
@@ -3917,6 +3922,11 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml
+- !!merge <<: *stablediffusionggml
+  name: "rocm-stablediffusion-ggml-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-stablediffusion-ggml"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-stablediffusion-ggml
 - !!merge <<: *stablediffusionggml
   name: "intel-sycl-f32-stablediffusion-ggml-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-stablediffusion-ggml"