Merge branch 'ggml-org:master' into acc_type_vec2

Author: SavicStefan

.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/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/workflows/build-amd.yml

@@ -0,0 +1,52 @@
+name: CI (AMD)
+
+on:
+  workflow_dispatch: # allows manual triggering
+  push:
+    branches:
+      - master
+    paths: [
+      '.github/workflows/build-amd.yml',
+      '**/CMakeLists.txt',
+      '**/.cmake',
+      '**/*.h',
+      '**/*.hpp',
+      '**/*.c',
+      '**/*.cpp',
+      '**/*.cu',
+      '**/*.cuh',
+      '**/*.comp'
+    ]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  ggml-ci-x64-amd-vulkan:
+    runs-on: [self-hosted, Linux, X64, AMD]
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v4
+
+      - name: Test
+        id: ggml-ci
+        run: |
+          vulkaninfo --summary
+          GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
+
+  ggml-ci-x64-amd-rocm:
+    runs-on: [self-hosted, Linux, X64, AMD]
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v4
+
+      - name: Test
+        id: ggml-ci
+        run: |
+          amd-smi static
+          GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp

.github/workflows/build-linux-cross.yml

@@ -141,97 +141,6 @@ jobs:
 
   #         cmake --build build --config Release -j $(nproc)
 
-  ubuntu-24-ppc64el-cpu-cross:
-    runs-on: ubuntu-24.04
-
-    steps:
-      - uses: actions/checkout@v4
-      - name: Setup PowerPC64le
-        run: |
-          sudo dpkg --add-architecture ppc64el
-
-          # Add arch-specific repositories for non-amd64 architectures
-          cat << EOF | sudo tee /etc/apt/sources.list.d/ppc64el-ports.list
-          deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
-          deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
-          deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
-          deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
-          EOF
-
-          sudo apt-get update || true    ;# Prevent failure due to missing URLs.
-
-          sudo apt-get install -y --no-install-recommends \
-                  build-essential \
-                  gcc-14-powerpc64le-linux-gnu \
-                  g++-14-powerpc64le-linux-gnu
-
-      - name: Build
-        run: |
-          cmake -B build -DLLAMA_CURL=OFF \
-                         -DCMAKE_BUILD_TYPE=Release \
-                         -DGGML_OPENMP=OFF \
-                         -DLLAMA_BUILD_EXAMPLES=ON \
-                         -DLLAMA_BUILD_TOOLS=ON \
-                         -DLLAMA_BUILD_TESTS=OFF \
-                         -DCMAKE_SYSTEM_NAME=Linux \
-                         -DCMAKE_SYSTEM_PROCESSOR=ppc64 \
-                         -DCMAKE_C_COMPILER=powerpc64le-linux-gnu-gcc-14 \
-                         -DCMAKE_CXX_COMPILER=powerpc64le-linux-gnu-g++-14 \
-                         -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-                         -DCMAKE_FIND_ROOT_PATH=/usr/lib/powerpc64le-linux-gnu \
-                         -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-                         -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-                         -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
-
-          cmake --build build --config Release -j $(nproc)
-
-  # ubuntu-24-ppc64el-vulkan-cross:
-  #   runs-on: ubuntu-24.04
-
-  #   steps:
-  #     - uses: actions/checkout@v4
-  #     - name: Setup PowerPC64le
-  #       run: |
-  #         sudo dpkg --add-architecture ppc64el
-
-  #         # Add arch-specific repositories for non-amd64 architectures
-  #         cat << EOF | sudo tee /etc/apt/sources.list.d/ppc64el-ports.list
-  #         deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
-  #         deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
-  #         deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
-  #         deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
-  #         EOF
-
-  #         sudo apt-get update || true    ;# Prevent failure due to missing URLs.
-
-  #         sudo apt-get install -y --no-install-recommends \
-  #                 build-essential \
-  #                 glslc \
-  #                 gcc-14-powerpc64le-linux-gnu \
-  #                 g++-14-powerpc64le-linux-gnu \
-  #                 libvulkan-dev:ppc64el
-
-  #     - name: Build
-  #       run: |
-  #         cmake -B build -DLLAMA_CURL=OFF \
-  #                        -DCMAKE_BUILD_TYPE=Release \
-  #                        -DGGML_VULKAN=ON \
-  #                        -DGGML_OPENMP=OFF \
-  #                        -DLLAMA_BUILD_EXAMPLES=ON \
-  #                        -DLLAMA_BUILD_TOOLS=ON \
-  #                        -DLLAMA_BUILD_TESTS=OFF \
-  #                        -DCMAKE_SYSTEM_NAME=Linux \
-  #                        -DCMAKE_SYSTEM_PROCESSOR=ppc64 \
-  #                        -DCMAKE_C_COMPILER=powerpc64le-linux-gnu-gcc-14 \
-  #                        -DCMAKE_CXX_COMPILER=powerpc64le-linux-gnu-g++-14 \
-  #                        -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-  #                        -DCMAKE_FIND_ROOT_PATH=/usr/lib/powerpc64le-linux-gnu \
-  #                        -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-  #                        -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-  #                        -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
-
-  #         cmake --build build --config Release -j $(nproc)
-
   debian-13-loongarch64-cpu-cross:
     runs-on: ubuntu-24.04
     container: debian@sha256:653dfb9f86c3782e8369d5f7d29bb8faba1f4bff9025db46e807fa4c22903671
@@ -344,3 +253,47 @@ jobs:
                          -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
 
           cmake --build build --config Release -j $(nproc)
+
+  ubuntu-24-riscv64-cpu-spacemit-ime-cross:
+    runs-on: ubuntu-24.04
+
+    env:
+      SPACEMIT_IME_TOOLCHAIN_VERSION: "1.1.2"
+      SPACEMIT_IME_TOOLCHAIN_PATH: "spacemit-toolchain-linux-glibc-x86_64"
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Cache Toolchain
+        uses: actions/cache@v4
+        id: cache-spacemit-ime-cross-toolchain
+        with:
+          path: ./${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}
+          key: ${{ runner.os }}-spacemit-ime-toolchain-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
+
+      - name: Setup Toolchain
+        if: steps.cache-spacemit-ime-cross-toolchain.outputs.cache-hit != 'true'
+        run: |
+          wget --quiet --no-check-certificate https://archive.spacemit.com/toolchain/spacemit-toolchain-linux-glibc-x86_64-v${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}.tar.xz -O ${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}.tar.xz
+          rm -rf ${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}
+          mkdir -p ${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}
+          tar xf ${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}.tar.xz -C ${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }} --strip-components=1
+          rm -rf ${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}.tar.xz
+
+      - name: Build
+        run: |
+          export RISCV_ROOT_PATH=${PWD}/${{ env.SPACEMIT_IME_TOOLCHAIN_PATH }}
+          cmake -B build -DLLAMA_CURL=OFF \
+                         -DCMAKE_BUILD_TYPE=Release \
+                         -DGGML_OPENMP=OFF \
+                         -DLLAMA_BUILD_EXAMPLES=ON \
+                         -DLLAMA_BUILD_TOOLS=ON \
+                         -DLLAMA_BUILD_TESTS=OFF \
+                         -DGGML_CPU_RISCV64_SPACEMIT=ON \
+                         -DGGML_RVV=ON \
+                         -DGGML_RV_ZFH=ON \
+                         -DGGML_RV_ZICBOP=ON \
+                         -DRISCV64_SPACEMIT_IME_SPEC=RISCV64_SPACEMIT_IME1 \
+                         -DCMAKE_TOOLCHAIN_FILE=${PWD}/cmake/riscv64-spacemit-linux-gnu-gcc.cmake
+
+          cmake --build build --config Release -j $(nproc)