Merge pull request #263 from menloresearch/update-dev-from-master-2025-09-27-00-32

Sync master with upstream release b6602

Author: jan-service-account

.devops/musa.Dockerfile

@@ -1,10 +1,10 @@
 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
+ARG BASE_MUSA_DEV_CONTAINER=sh-harbor.mthreads.com/haive/mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
 
-ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
+ARG BASE_MUSA_RUN_CONTAINER=sh-harbor.mthreads.com/haive/mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 

.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

.github/workflows/build.yml

@@ -192,6 +192,10 @@ jobs:
             os: ubuntu-22.04
           - build: 'arm64'
             os: ubuntu-22.04-arm
+          - build: 's390x'
+            os: ubuntu-24.04-s390x
+          - build: 'ppc64le'
+            os: ubuntu-24.04-ppc64le
 
     runs-on: ${{ matrix.os }}
 
@@ -206,11 +210,28 @@ jobs:
           key: ubuntu-cpu-cmake
           evict-old-files: 1d
 
-      - name: Dependencies
-        id: depends
+      - name: Build Dependencies
+        id: build_depends
         run: |
           sudo apt-get update
-          sudo apt-get install build-essential libcurl4-openssl-dev
+          sudo apt-get install -y --no-install-recommends \
+            python3 python3-pip python3-dev \
+            libjpeg-dev build-essential libcurl4-openssl-dev \
+            git-lfs
+
+      - name: Python Dependencies
+        id: python_depends
+        run: |
+          python3 -m pip install --upgrade pip
+          pip3 install ./gguf-py
+
+      - name: Swap Endianness
+        id: endianness
+        if: ${{ matrix.build == 's390x' }}
+        run: |
+          for f in models/*.gguf; do
+            echo YES | python3 gguf-py/gguf/scripts/gguf_convert_endian.py $f big
+          done
 
       - name: Build
         id: cmake_build
@@ -228,6 +249,7 @@ jobs:
 
       - name: Test llama2c conversion
         id: llama2c_test
+        if: ${{ matrix.build != 's390x' }}
         run: |
           cd build
           echo "Fetch tokenizer"
@@ -237,6 +259,15 @@ jobs:
           ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
           ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
+      - name: Test llama2c (s390x)
+        id: llama2c_test_s390x
+        if: ${{ matrix.build == 's390x' }}
+        run: |
+          cd build
+          echo "Fetch llama2c big-endian model"
+          wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
+          ./bin/llama-cli -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+
   ubuntu-latest-cmake-sanitizer:
     runs-on: ubuntu-latest
 
@@ -475,7 +506,7 @@ jobs:
 
   ubuntu-22-cmake-musa:
     runs-on: ubuntu-22.04
-    container: mthreads/musa:rc4.2.0-devel-ubuntu22.04-amd64
+    container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64
 
     steps:
       - name: Clone

.github/workflows/docker.yml

@@ -68,40 +68,36 @@ jobs:
           username: ${{ github.repository_owner }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Determine tag name
+      - name: Determine source tag name
+        id: srctag
+        uses: ./.github/actions/get-tag-name
+        env:
+          BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
+
+      - name: Determine image tag name
         id: tag
         shell: bash
         run: |
-          BUILD_NUMBER="$(git rev-list --count HEAD)"
-          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
           REPO_OWNER="${GITHUB_REPOSITORY_OWNER@L}"  # to lower case
           REPO_NAME="${{ github.event.repository.name }}"
 
-          # determine tag name postfix (build number, commit hash)
-          if [[ "${{ env.GITHUB_BRANCH_NAME }}" == "master" ]]; then
-            TAG_POSTFIX="-b${BUILD_NUMBER}"
-          else
-            SAFE_NAME=$(echo "${{ env.GITHUB_BRANCH_NAME }}" | tr '/' '-')
-            TAG_POSTFIX="-${SAFE_NAME}-${SHORT_HASH}"
-          fi
           # list all tags possible
           if [[ "${{ matrix.config.tag }}" == "cpu" ]]; then
               TYPE=""
           else
               TYPE="-${{ matrix.config.tag }}"
           fi
           PREFIX="ghcr.io/${REPO_OWNER}/${REPO_NAME}:"
-          FULLTAGS="${PREFIX}full${TYPE},${PREFIX}full${TYPE}${TAG_POSTFIX}"
-          LIGHTTAGS="${PREFIX}light${TYPE},${PREFIX}light${TYPE}${TAG_POSTFIX}"
-          SERVERTAGS="${PREFIX}server${TYPE},${PREFIX}server${TYPE}${TAG_POSTFIX}"
+          FULLTAGS="${PREFIX}full${TYPE},${PREFIX}full${TYPE}-${{ steps.srctag.outputs.name }}"
+          LIGHTTAGS="${PREFIX}light${TYPE},${PREFIX}light${TYPE}-${{ steps.srctag.outputs.name }}"
+          SERVERTAGS="${PREFIX}server${TYPE},${PREFIX}server${TYPE}-${{ steps.srctag.outputs.name }}"
           echo "full_output_tags=$FULLTAGS" >> $GITHUB_OUTPUT
           echo "light_output_tags=$LIGHTTAGS" >> $GITHUB_OUTPUT
           echo "server_output_tags=$SERVERTAGS" >> $GITHUB_OUTPUT
           echo "full_output_tags=$FULLTAGS"  # print out for debugging
           echo "light_output_tags=$LIGHTTAGS"  # print out for debugging
           echo "server_output_tags=$SERVERTAGS"  # print out for debugging
         env:
-          GITHUB_BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
           GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
 
       - name: Free Disk Space (Ubuntu)
@@ -177,3 +173,29 @@ jobs:
           # return to this if the experimental github cache is having issues
           #cache-to: type=local,dest=/tmp/.buildx-cache
           #cache-from: type=local,src=/tmp/.buildx-cache
+
+  create_tag:
+    name: Create and push git tag
+    runs-on: ubuntu-22.04
+    permissions:
+      contents: write
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Determine source tag name
+        id: srctag
+        uses: ./.github/actions/get-tag-name
+        env:
+          BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
+
+      - name: Create and push git tag
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          git tag ${{ steps.srctag.outputs.name }} || exit 0
+          git push origin ${{ steps.srctag.outputs.name }} || exit 0

.gitignore

@@ -149,6 +149,6 @@ poetry.toml
 /run-chat.sh
 .ccache/
 
-# Code Workspace
+# IDE
 *.code-workspace
-
+.windsurf/

.windsurf/rules/css-architecture.md

@@ -61,6 +61,7 @@
 /ggml/src/ggml-metal/                   @ggerganov
 /ggml/src/ggml-opt.cpp                  @JohannesGaessler
 /ggml/src/ggml-quants.*                 @ggerganov
+/ggml/src/ggml-rpc/                     @rgerganov
 /ggml/src/ggml-threading.*              @ggerganov @slaren
 /ggml/src/ggml-vulkan/                  @0cc4m
 /ggml/src/ggml-zdnn/                    @taronaeo @Andreas-Krebbel @AlekseiNikiforovIBM
@@ -89,6 +90,7 @@
 /tools/mtmd/                            @ngxson
 /tools/perplexity/                      @ggerganov
 /tools/quantize/                        @ggerganov
+/tools/rpc/                             @rgerganov
 /tools/run/                             @ericcurtin
 /tools/server/*                         @ngxson @ggerganov @ericcurtin # no subdir
 /tools/server/webui/                    @allozaur
@@ -103,4 +105,5 @@
 /LICENSE                                @ggerganov
 /README.md                              @ggerganov
 /SECURITY.md                            @ggerganov
+/build-xcframework.sh                   @danbev
 requirements*.txt                       @CISC