diff --git a/Dockerfile.rocm b/Dockerfile.rocm
index 4ea7a1d7..0e22355b 100644
--- a/Dockerfile.rocm
+++ b/Dockerfile.rocm
@@ -59,18 +59,17 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
         curl \
         git \
         git-lfs \
-        hipblas-dev \
-        hipblaslt-dev \
-        hipcub-dev \
         libcurl4-openssl-dev \
         ninja-build \
         pkg-config \
         python3 \
-        rocblas-dev \
-        rocprim-dev \
-        rocwmma-dev \
     && rm -rf /var/lib/apt/lists/*
 
+# Ubuntu jammy ships cmake 3.22, which predates the block command that
+# ROCm 7.14 hipblaslt-config.cmake requires (CMake >= 3.25). Install the
+# official 3.31 binary; /usr/local/bin precedes /usr/bin on PATH.
+RUN curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.31.6/cmake-3.31.6-linux-x86_64.tar.gz     | tar -xz -C /usr/local --strip-components=1
+
 WORKDIR /src
 
 # COPY ordering mirrors the CUDA Dockerfile: C++ build inputs first so the
@@ -152,11 +151,8 @@ ENV PATH=/opt/rocm/bin:${PATH}
 RUN apt-get update && apt-get install -y --no-install-recommends \
         ca-certificates \
         curl \
-        hipblas \
-        hipblaslt \
         libgomp1 \
         pciutils \
-        rocblas \
     && rm -rf /var/lib/apt/lists/*
 
 # uv (pinned) manages Python 3.12 + resolves the luce + pflash
diff --git a/server/deps/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu b/server/deps/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu
index 1e6ca455..5f4b3035 100644
--- a/server/deps/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/server/deps/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -3916,6 +3916,12 @@ static void ggml_backend_cuda_synchronize(ggml_backend_t backend) {
     GGML_UNUSED(backend);
 }
 
+// (moved above the USE_CUDA_GRAPH guard: ggml_cuda_node_is_noop
+// calls this unconditionally)
+static bool ggml_cuda_node_launches_nothing(const ggml_tensor * node) {
+    return ggml_is_empty(node) || node->op == GGML_OP_RESHAPE || node->op == GGML_OP_TRANSPOSE ||
+        node->op == GGML_OP_VIEW || node->op == GGML_OP_PERMUTE || node->op == GGML_OP_NONE;
+}
 #ifdef USE_CUDA_GRAPH
 
 // GGML_CUDA_COLLECTIVE_GRAPH_CAPTURE=1: allow graph capture of a graph that
@@ -3930,10 +3936,6 @@ static bool ggml_cuda_cluster_capture_allowed() {
 }
 
 // View-like and empty nodes: the evaluation loops launch nothing for them.
-static bool ggml_cuda_node_launches_nothing(const ggml_tensor * node) {
-    return ggml_is_empty(node) || node->op == GGML_OP_RESHAPE || node->op == GGML_OP_TRANSPOSE ||
-        node->op == GGML_OP_VIEW || node->op == GGML_OP_PERMUTE || node->op == GGML_OP_NONE;
-}
 
 static bool ggml_cuda_graph_check_compability(ggml_cgraph * cgraph) {