fix(rocm): add gfx1151 support and expose AMDGPU_TARGETS build-arg

Add gfx1151 (AMD Strix Halo / Ryzen AI MAX) to the default AMDGPU_TARGETS
list in the llama-cpp backend Makefile. ROCm 7.2.1 ships with gfx1151
Tensile libraries, so this architecture should be included in default builds.

Also expose AMDGPU_TARGETS as an ARG/ENV in Dockerfile.llama-cpp so that
users building for non-default GPU architectures can override the target
list via --build-arg AMDGPU_TARGETS=<arch>. Previously, passing
-DAMDGPU_TARGETS=<arch> through CMAKE_ARGS was silently overridden by
the Makefile's own append of the default target list.

Fixes #9374

Signed-off-by: Keith Mattix <keithmattix2@gmail.com>

Author: keithmattix

backend/Dockerfile.llama-cpp

@@ -58,6 +58,8 @@ ARG CUDA_DOCKER_ARCH
 ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
 ARG CMAKE_ARGS
 ENV CMAKE_ARGS=${CMAKE_ARGS}
+ARG AMDGPU_TARGETS
+ENV AMDGPU_TARGETS=${AMDGPU_TARGETS}
 ARG BACKEND=rerankers
 ARG BUILD_TYPE
 ENV BUILD_TYPE=${BUILD_TYPE}

backend/cpp/llama-cpp/Makefile

@@ -33,7 +33,7 @@ else ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_PATH ?= /opt/rocm
 	export CXX=$(ROCM_HOME)/llvm/bin/clang++
 	export CC=$(ROCM_HOME)/llvm/bin/clang
-	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
+	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
 	CMAKE_ARGS+=-DGGML_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
 else ifeq ($(BUILD_TYPE),vulkan)
 	CMAKE_ARGS+=-DGGML_VULKAN=1