diff --git a/.devops/full-cuda.Dockerfile b/.devops/full-cuda.Dockerfile
index 2a7da586a..61f671465 100644
--- a/.devops/full-cuda.Dockerfile
+++ b/.devops/full-cuda.Dockerfile
@@ -6,7 +6,7 @@ ARG CUDA_VERSION=11.7.1
 # Target the CUDA build image
 ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
 
-FROM ${BASE_CUDA_DEV_CONTAINER} as build
+FROM ${BASE_CUDA_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 ARG CUDA_DOCKER_ARCH=all
diff --git a/.devops/full-rocm.Dockerfile b/.devops/full-rocm.Dockerfile
index 5cbd2e7a1..680d1cb92 100644
--- a/.devops/full-rocm.Dockerfile
+++ b/.devops/full-rocm.Dockerfile
@@ -6,7 +6,7 @@ ARG ROCM_VERSION=5.6
 # Target the CUDA build image
 ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
 
-FROM ${BASE_ROCM_DEV_CONTAINER} as build
+FROM ${BASE_ROCM_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 # List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
diff --git a/.devops/full.Dockerfile b/.devops/full.Dockerfile
index 6f19afa9c..2a06f82b7 100644
--- a/.devops/full.Dockerfile
+++ b/.devops/full.Dockerfile
@@ -1,6 +1,6 @@
 ARG UBUNTU_VERSION=22.04
 
-FROM ubuntu:$UBUNTU_VERSION as build
+FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
     apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
diff --git a/.devops/llama-cli-cuda.Dockerfile b/.devops/llama-cli-cuda.Dockerfile
index bff946cbc..8eda63a89 100644
--- a/.devops/llama-cli-cuda.Dockerfile
+++ b/.devops/llama-cli-cuda.Dockerfile
@@ -6,7 +6,7 @@ ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VER
 # Target the CUDA runtime image
 ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
 
-FROM ${BASE_CUDA_DEV_CONTAINER} as build
+FROM ${BASE_CUDA_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 ARG CUDA_DOCKER_ARCH=all
@@ -25,7 +25,7 @@ ENV GGML_CUDA=1
 
 RUN make -j$(nproc) llama-cli
 
-FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
+FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
 
 RUN apt-get update && \
     apt-get install -y libgomp1
diff --git a/.devops/llama-cli-intel.Dockerfile b/.devops/llama-cli-intel.Dockerfile
index bd816f9f5..2bf82bb58 100644
--- a/.devops/llama-cli-intel.Dockerfile
+++ b/.devops/llama-cli-intel.Dockerfile
@@ -1,6 +1,6 @@
 ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04
 
-FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
+FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
 
 ARG GGML_SYCL_F16=OFF
 RUN apt-get update && \
@@ -17,7 +17,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
     cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16} && \
     cmake --build build --config Release --target llama-cli
 
-FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
+FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
 
 COPY --from=build /app/build/bin/llama-cli /llama-cli
 
diff --git a/.devops/llama-cli-rocm.Dockerfile b/.devops/llama-cli-rocm.Dockerfile
index caa507b08..c3d1ab067 100644
--- a/.devops/llama-cli-rocm.Dockerfile
+++ b/.devops/llama-cli-rocm.Dockerfile
@@ -6,7 +6,7 @@ ARG ROCM_VERSION=5.6
 # Target the CUDA build image
 ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
 
-FROM ${BASE_ROCM_DEV_CONTAINER} as build
+FROM ${BASE_ROCM_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 # List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
diff --git a/.devops/llama-cli-vulkan.Dockerfile b/.devops/llama-cli-vulkan.Dockerfile
index 6155d5881..9b0dad8bf 100644
--- a/.devops/llama-cli-vulkan.Dockerfile
+++ b/.devops/llama-cli-vulkan.Dockerfile
@@ -1,6 +1,6 @@
 ARG UBUNTU_VERSION=jammy
 
-FROM ubuntu:$UBUNTU_VERSION as build
+FROM ubuntu:$UBUNTU_VERSION AS build
 
 # Install build tools
 RUN apt update && apt install -y git build-essential cmake wget libgomp1
diff --git a/.devops/llama-cli.Dockerfile b/.devops/llama-cli.Dockerfile
index 38382bfc9..7f741aa46 100644
--- a/.devops/llama-cli.Dockerfile
+++ b/.devops/llama-cli.Dockerfile
@@ -1,6 +1,6 @@
 ARG UBUNTU_VERSION=22.04
 
-FROM ubuntu:$UBUNTU_VERSION as build
+FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
     apt-get install -y build-essential git
@@ -11,7 +11,7 @@ COPY . .
 
 RUN make -j$(nproc) llama-cli
 
-FROM ubuntu:$UBUNTU_VERSION as runtime
+FROM ubuntu:$UBUNTU_VERSION AS runtime
 
 RUN apt-get update && \
     apt-get install -y libgomp1
diff --git a/.devops/llama-server-cuda.Dockerfile b/.devops/llama-server-cuda.Dockerfile
index d7eaa0925..67328cf1c 100644
--- a/.devops/llama-server-cuda.Dockerfile
+++ b/.devops/llama-server-cuda.Dockerfile
@@ -6,7 +6,7 @@ ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VER
 # Target the CUDA runtime image
 ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
 
-FROM ${BASE_CUDA_DEV_CONTAINER} as build
+FROM ${BASE_CUDA_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 ARG CUDA_DOCKER_ARCH=all
@@ -27,7 +27,7 @@ ENV LLAMA_CURL=1
 
 RUN make -j$(nproc) llama-server
 
-FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
+FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
 
 RUN apt-get update && \
     apt-get install -y libcurl4-openssl-dev libgomp1 curl
diff --git a/.devops/llama-server-intel.Dockerfile b/.devops/llama-server-intel.Dockerfile
index 8f8fef8c0..eb9aba618 100644
--- a/.devops/llama-server-intel.Dockerfile
+++ b/.devops/llama-server-intel.Dockerfile
@@ -1,6 +1,6 @@
 ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04
 
-FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
+FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
 
 ARG GGML_SYCL_F16=OFF
 RUN apt-get update && \
@@ -17,7 +17,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
     cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
     cmake --build build --config Release --target llama-server
 
-FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
+FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
 
 RUN apt-get update && \
     apt-get install -y libcurl4-openssl-dev curl
diff --git a/.devops/llama-server-rocm.Dockerfile b/.devops/llama-server-rocm.Dockerfile
index af96c3325..763b4cd3f 100644
--- a/.devops/llama-server-rocm.Dockerfile
+++ b/.devops/llama-server-rocm.Dockerfile
@@ -6,7 +6,7 @@ ARG ROCM_VERSION=5.6
 # Target the CUDA build image
 ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
 
-FROM ${BASE_ROCM_DEV_CONTAINER} as build
+FROM ${BASE_ROCM_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 # List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878
diff --git a/.devops/llama-server-vulkan.Dockerfile b/.devops/llama-server-vulkan.Dockerfile
index 49062f84b..13a61ffd8 100644
--- a/.devops/llama-server-vulkan.Dockerfile
+++ b/.devops/llama-server-vulkan.Dockerfile
@@ -1,6 +1,6 @@
 ARG UBUNTU_VERSION=jammy
 
-FROM ubuntu:$UBUNTU_VERSION as build
+FROM ubuntu:$UBUNTU_VERSION AS build
 
 # Install build tools
 RUN apt update && apt install -y git build-essential cmake wget
diff --git a/.devops/llama-server.Dockerfile b/.devops/llama-server.Dockerfile
index a53a5c999..b631d5806 100644
--- a/.devops/llama-server.Dockerfile
+++ b/.devops/llama-server.Dockerfile
@@ -1,6 +1,6 @@
 ARG UBUNTU_VERSION=22.04
 
-FROM ubuntu:$UBUNTU_VERSION as build
+FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
     apt-get install -y build-essential git libcurl4-openssl-dev curl
@@ -13,7 +13,7 @@ ENV LLAMA_CURL=1
 
 RUN make -j$(nproc) llama-server
 
-FROM ubuntu:$UBUNTU_VERSION as runtime
+FROM ubuntu:$UBUNTU_VERSION AS runtime
 
 RUN apt-get update && \
     apt-get install -y libcurl4-openssl-dev libgomp1