Merge upstream/master

Author: MrAMS

.devops/intel.Dockerfile

@@ -1,8 +1,8 @@
-ARG ONEAPI_VERSION=2025.1.1-0-devel-ubuntu24.04
+ARG ONEAPI_VERSION=2025.2.2-0-devel-ubuntu24.04
 
 ## Build Image
 
-FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
+FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS build
 
 ARG GGML_SYCL_F16=OFF
 RUN apt-get update && \
@@ -31,7 +31,7 @@ RUN mkdir -p /app/full \
     && cp requirements.txt /app/full \
     && cp .devops/tools.sh /app/full/tools.sh
 
-FROM intel/oneapi-basekit:$ONEAPI_VERSION AS base
+FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS base
 
 RUN apt-get update \
     && apt-get install -y libgomp1 curl\

.devops/musa.Dockerfile

@@ -1,6 +1,6 @@
 ARG UBUNTU_VERSION=22.04
 # This needs to generally match the container host's environment.
-ARG MUSA_VERSION=rc4.2.0
+ARG MUSA_VERSION=rc4.3.0
 # Target the MUSA build image
 ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
 

.devops/nix/package.nix

@@ -128,10 +128,6 @@ effectiveStdenv.mkDerivation (finalAttrs: {
   };
 
   postPatch = ''
-    substituteInPlace ./ggml/src/ggml-metal/ggml-metal.m \
-      --replace '[bundle pathForResource:@"ggml-metal" ofType:@"metal"];' "@\"$out/bin/ggml-metal.metal\";"
-    substituteInPlace ./ggml/src/ggml-metal/ggml-metal.m \
-      --replace '[bundle pathForResource:@"default" ofType:@"metallib"];' "@\"$out/bin/default.metallib\";"
   '';
 
   # With PR#6015 https://github.com/ggml-org/llama.cpp/pull/6015,

.devops/rocm.Dockerfile

@@ -1,8 +1,8 @@
 ARG UBUNTU_VERSION=24.04
 
 # This needs to generally match the container host's environment.
-ARG ROCM_VERSION=6.4
-ARG AMDGPU_VERSION=6.4
+ARG ROCM_VERSION=7.0
+ARG AMDGPU_VERSION=7.0
 
 # Target the ROCm build image
 ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
@@ -13,9 +13,8 @@ FROM ${BASE_ROCM_DEV_CONTAINER} AS build
 # Unless otherwise specified, we make a fat build.
 # List from https://github.com/ggml-org/llama.cpp/pull/1087#issuecomment-1682807878
 # This is mostly tied to rocBLAS supported archs.
-# gfx803, gfx900, gfx1032, gfx1101, gfx1102,not officialy supported
-# gfx906 is deprecated
-#check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.1/reference/system-requirements.html
+# gfx803, gfx900, gfx906, gfx1032, gfx1101, gfx1102,not officialy supported
+# check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.1/reference/system-requirements.html
 
 ARG ROCM_DOCKER_ARCH='gfx803;gfx900;gfx906;gfx908;gfx90a;gfx942;gfx1010;gfx1030;gfx1032;gfx1100;gfx1101;gfx1102;gfx1200;gfx1201;gfx1151'
 #ARG ROCM_DOCKER_ARCH='gfx1151'
@@ -36,13 +35,10 @@ WORKDIR /app
 
 COPY . .
 
-RUN git clone https://github.com/rocm/rocwmma --branch develop --depth 1
-
 RUN HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
     cmake -S . -B build \
         -DGGML_HIP=ON \
         -DGGML_HIP_ROCWMMA_FATTN=ON \
-        -DCMAKE_HIP_FLAGS="-I$(pwd)/rocwmma/library/include/" \
         -DAMDGPU_TARGETS="$ROCM_DOCKER_ARCH" \
         -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON \
         -DCMAKE_BUILD_TYPE=Release -DLLAMA_BUILD_TESTS=OFF \

.devops/s390x.Dockerfile

@@ -2,10 +2,10 @@ ARG GCC_VERSION=15.2.0
 ARG UBUNTU_VERSION=24.04
 
 ### Build Llama.cpp stage
-FROM --platform=linux/s390x gcc:${GCC_VERSION} AS build
+FROM gcc:${GCC_VERSION} AS build
 
-RUN --mount=type=cache,target=/var/cache/apt \
-    --mount=type=cache,target=/var/lib/apt/lists \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
     apt update -y && \
     apt upgrade -y && \
     apt install -y --no-install-recommends \
@@ -40,7 +40,7 @@ COPY requirements     /opt/llama.cpp/gguf-py/requirements
 
 
 ### Collect all llama.cpp binaries, libraries and distro libraries
-FROM --platform=linux/s390x scratch AS collector
+FROM scratch AS collector
 
 # Copy llama.cpp binaries and libraries
 COPY --from=build /opt/llama.cpp/bin     /llama.cpp/bin
@@ -49,13 +49,14 @@ COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
 
 
 ### Base image
-FROM --platform=linux/s390x ubuntu:${UBUNTU_VERSION} AS base
+FROM ubuntu:${UBUNTU_VERSION} AS base
 
-RUN --mount=type=cache,target=/var/cache/apt \
-    --mount=type=cache,target=/var/lib/apt/lists \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
     apt update -y && \
     apt install -y --no-install-recommends \
         # WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
+        # See: https://github.com/ggml-org/llama.cpp/pull/15915#issuecomment-3317166506
         curl libgomp1 libopenblas-dev && \
     apt autoremove -y && \
     apt clean -y && \
@@ -68,13 +69,13 @@ COPY --from=collector /llama.cpp/lib /usr/lib/s390x-linux-gnu
 
 
 ### Full
-FROM --platform=linux/s390x base AS full
+FROM base AS full
 
 ENV PATH="/root/.cargo/bin:${PATH}"
 WORKDIR /app
 
-RUN --mount=type=cache,target=/var/cache/apt \
-    --mount=type=cache,target=/var/lib/apt/lists \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
     apt update -y && \
     apt install -y \
         git cmake libjpeg-dev \
@@ -97,7 +98,7 @@ ENTRYPOINT [ "/app/tools.sh" ]
 
 
 ### CLI Only
-FROM --platform=linux/s390x base AS light
+FROM base AS light
 
 WORKDIR /llama.cpp/bin
 
@@ -108,7 +109,7 @@ ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]
 
 
 ### Server
-FROM --platform=linux/s390x base AS server
+FROM base AS server
 
 ENV LLAMA_ARG_HOST=0.0.0.0
 

.github/actions/install-exe/action.yml

@@ -0,0 +1,36 @@
+name: "Install exe"
+description: "Download and install exe"
+inputs:
+  url:
+    description: "URL of the exe installer"
+    required: true
+  args:
+    description: "Installer arguments"
+    required: true
+  timeout:
+    description: "Timeout (in ms)"
+    required: false
+    default: "600000"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Install EXE
+      shell: pwsh
+      run: |
+        $ErrorActionPreference = "Stop"
+        write-host "Downloading Installer EXE"
+        Invoke-WebRequest -Uri "${{ inputs.url }}" -OutFile "${env:RUNNER_TEMP}\temp-install.exe"
+        write-host "Installing"
+        $proc = Start-Process "${env:RUNNER_TEMP}\temp-install.exe" -ArgumentList '${{ inputs.args }}' -NoNewWindow -PassThru
+        $completed = $proc.WaitForExit(${{ inputs.timeout }})
+        if (-not $completed) {
+            Write-Error "Installer timed out. Killing the process"
+            $proc.Kill()
+            exit 1
+        }
+        if ($proc.ExitCode -ne 0) {
+            Write-Error "Installer failed with exit code $($proc.ExitCode)"
+            exit 1
+        }
+        write-host "Completed installation"

.github/actions/linux-setup-spacemit/action.yml

@@ -0,0 +1,20 @@
+name: "Linux - Setup SpacemiT Toolchain"
+description: "Setup SpacemiT Toolchain for Linux"
+inputs:
+  path:
+    description: "Installation path"
+    required: true
+  version:
+    description: "SpacemiT toolchain version"
+    required: true
+
+runs:
+  using: "composite"
+  steps:
+    - name: Setup SpacemiT Toolchain
+      id: setup
+      uses: ./.github/actions/unarchive-tar
+      with:
+        url: https://archive.spacemit.com/toolchain/spacemit-toolchain-linux-glibc-x86_64-v${{ inputs.version }}.tar.xz
+        path: ${{ inputs.path }}
+        strip: 1

.github/actions/linux-setup-vulkan/action.yml

@@ -0,0 +1,20 @@
+name: "Linux - Setup Vulkan SDK"
+description: "Setup Vulkan SDK for Linux"
+inputs:
+  path:
+    description: "Installation path"
+    required: true
+  version:
+    description: "Vulkan SDK version"
+    required: true
+
+runs:
+  using: "composite"
+  steps:
+    - name: Setup Vulkan SDK
+      id: setup
+      uses: ./.github/actions/unarchive-tar
+      with:
+        url: https://sdk.lunarg.com/sdk/download/${{ inputs.version }}/linux/vulkan_sdk.tar.xz
+        path: ${{ inputs.path }}
+        strip: 1

.github/actions/unarchive-tar/action.yml

@@ -0,0 +1,27 @@
+name: "Unarchive tar"
+description: "Download and unarchive tar into directory"
+inputs:
+  url:
+    description: "URL of the tar archive"
+    required: true
+  path:
+    description: "Directory to unarchive into"
+    required: true
+  type:
+    description: "Compression type (tar option)"
+    required: false
+    default: "J"
+  strip:
+    description: "Strip components"
+    required: false
+    default: "0"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Unarchive into directory
+      shell: bash
+      run: |
+        mkdir -p ${{ inputs.path }}
+        cd ${{ inputs.path }}
+        curl --no-progress-meter ${{ inputs.url }} | tar -${{ inputs.type }}x --strip-components=${{ inputs.strip }}

.github/actions/windows-setup-rocm/action.yml

@@ -0,0 +1,15 @@
+name: "Windows - Setup ROCm"
+description: "Setup ROCm for Windows"
+inputs:
+  version:
+    description: "ROCm version"
+    required: true
+
+runs:
+  using: "composite"
+  steps:
+    - name: Setup ROCm
+      uses: ./.github/actions/install-exe
+      with:
+        url: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-${{ inputs.version }}-WinSvr2022-For-HIP.exe
+        args: -install