Merge main into tojson-unicode

Author: abetlen

.github/workflows/build-and-release.yaml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-20.04, windows-2019, macos-12]
+        os: [ubuntu-22.04, windows-2022, macos-14, macos-15]
 
     steps:
       - uses: actions/checkout@v4
@@ -21,18 +21,47 @@ jobs:
       # Used to host cibuildwheel
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.8"
+          python-version: "3.9"
 
-      - name: Install dependencies
+      - name: Install dependencies (Linux/MacOS)
+        if: runner.os != 'Windows'
         run: |
           python -m pip install --upgrade pip
-          python -m pip install -e .[all]
+          python -m pip install uv
+          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
+        shell: bash
+
+      - name: Install dependencies (Windows)
+        if: runner.os == 'Windows'
+        env:
+          RUST_LOG: trace        
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          python -m uv pip install -e .[all] --verbose
+        shell: cmd
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.20.0
+        uses: pypa/cibuildwheel@v2.22.0
         env:
-          # disable repair
+          # Keep repair disabled by default for non-Linux platforms in this job.
           CIBW_REPAIR_WHEEL_COMMAND: ""
+          # Linux needs auditwheel repair so manylinux and musllinux wheels are
+          # published with distinct platform tags instead of generic linux tags.
+          CIBW_REPAIR_WHEEL_COMMAND_LINUX: "LD_LIBRARY_PATH=/project/llama_cpp/lib auditwheel repair -w {dest_dir} {wheel}"
+          # The release wheel is tagged py3-none, so one build per platform
+          # covers all supported Python versions and avoids duplicate names.
+          CIBW_BUILD_LINUX: "cp38-*"
+          CIBW_BUILD_MACOS: "cp39-*"
+          CIBW_BUILD_WINDOWS: "cp39-*"
+          # Skip cibuildwheel's default i686 sidecar and keep Linux release
+          # wheels on a portable x86_64 CPU baseline.
+          CIBW_ARCHS_LINUX: "auto64"
+          CIBW_ARCHS_WINDOWS: "AMD64"
+          CIBW_ENVIRONMENT_LINUX: CMAKE_ARGS="-DGGML_NATIVE=off"
+          # Keep macOS release wheels on a portable CPU baseline instead of
+          # inheriting the hosted runner's native flags.
+          CIBW_ENVIRONMENT_MACOS: CMAKE_ARGS="-DGGML_NATIVE=off"
         with:
           package-dir: .
           output-dir: wheelhouse
@@ -44,7 +73,55 @@ jobs:
 
   build_wheels_arm64:
     name: Build arm64 wheels
+    runs-on: ubuntu-24.04-arm
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: "recursive"
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.22.0
+        env:
+          CIBW_SKIP: "pp*"
+          CIBW_REPAIR_WHEEL_COMMAND: "LD_LIBRARY_PATH=$PWD/llama_cpp/lib auditwheel repair -w {dest_dir} {wheel}"
+          CIBW_ARCHS: "aarch64"
+          # Keep native arm64 builds on a portable CPU baseline instead of
+          # tuning wheels to the hosted runner.
+          CIBW_ENVIRONMENT: CMAKE_ARGS="-DGGML_NATIVE=off"
+          # The release wheel is tagged py3-none, so one build covers all
+          # supported Python versions and avoids duplicate wheel names.
+          CIBW_BUILD: "cp38-*"
+        with:
+          output-dir: wheelhouse
+
+      - name: Upload wheels as artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels_arm64
+          path: ./wheelhouse/*.whl
+
+  build_wheels_riscv64:
+    name: Build riscv64 wheels (${{ matrix.shard.name }})
     runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        shard:
+          - name: cp310
+            build: "cp310-*"
+            artifact: wheels_riscv64_cp310
+          - name: cp311
+            build: "cp311-*"
+            artifact: wheels_riscv64_cp311
+          - name: cp312
+            build: "cp312-*"
+            artifact: wheels_riscv64_cp312
+          - name: cp313
+            build: "cp313-*"
+            artifact: wheels_riscv64_cp313
+          - name: cp314
+            build: "cp314-*"
+            artifact: wheels_riscv64_cp314
     steps:
       - uses: actions/checkout@v4
         with:
@@ -53,22 +130,27 @@ jobs:
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
         with:
-          platforms: linux/arm64
+          platforms: linux/riscv64
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.20.0
+        uses: pypa/cibuildwheel@v3.1.2
         env:
           CIBW_SKIP: "*musllinux* pp*"
           CIBW_REPAIR_WHEEL_COMMAND: ""
-          CIBW_ARCHS: "aarch64"
-          CIBW_BUILD: "cp38-* cp39-* cp310-* cp311-* cp312-*"
+          CIBW_ARCHS: "riscv64"
+          # Build riscv64 wheels against a conservative baseline instead of
+          # enabling RVV-related extensions from the build container.
+          CIBW_ENVIRONMENT: CMAKE_ARGS="-DGGML_NATIVE=off -DGGML_RVV=off -DGGML_RV_ZFH=off -DGGML_RV_ZVFH=off -DGGML_RV_ZICBOP=off -DGGML_RV_ZIHINTPAUSE=off"
+          # Split the emulated riscv64 build into one Python version per job
+          # to minimize wall-clock time without changing the release artifacts.
+          CIBW_BUILD: ${{ matrix.shard.build }}
         with:
           output-dir: wheelhouse
 
       - name: Upload wheels as artifacts
         uses: actions/upload-artifact@v4
         with:
-          name: wheels_arm64
+          name: ${{ matrix.shard.artifact }}
           path: ./wheelhouse/*.whl
 
   build_sdist:
@@ -79,24 +161,44 @@ jobs:
       - uses: actions/checkout@v4
         with:
           submodules: "recursive"
+
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.8"
-      - name: Install dependencies
+          python-version: "3.9"
+
+      - name: Install dependencies (Linux/MacOS)
+        if: runner.os != 'Windows'
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          RUST_LOG=trace python -m uv pip install -e .[all] --verbose
+          python -m uv pip install build
+        shell: bash
+
+      - name: Install dependencies (Windows)
+        if: runner.os == 'Windows'
+        env:
+          RUST_LOG: trace        
         run: |
-          python -m pip install --upgrade pip build
-          python -m pip install -e .[all]
+          python -m pip install --upgrade pip
+          python -m pip install uv
+          python -m uv pip install -e .[all] --verbose
+          python -m uv pip install build
+        shell: cmd
+
       - name: Build source distribution
         run: |
           python -m build --sdist
+
       - uses: actions/upload-artifact@v4
         with:
           name: sdist
           path: ./dist/*.tar.gz
 
   release:
     name: Release
-    needs: [build_wheels, build_wheels_arm64, build_sdist]
+    needs: [build_wheels, build_wheels_arm64, build_wheels_riscv64, build_sdist]
+    if: startsWith(github.ref, 'refs/tags/')
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/build-docker.yaml

@@ -9,13 +9,22 @@ permissions:
 jobs:
   docker:
     name: Build and push Docker image
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4
         with:
           submodules: "recursive"
 
+      - name: Set image tag
+        run: |
+          if [[ "${GITHUB_REF_TYPE}" == "tag" ]]; then
+            image_tag="${GITHUB_REF_NAME}"
+          else
+            image_tag="${GITHUB_REF_NAME//\//-}"
+          fi
+          echo "IMAGE_TAG=$image_tag" >> "$GITHUB_ENV"
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
 
@@ -40,7 +49,7 @@ jobs:
           platforms: linux/amd64,linux/arm64
           tags: |
             ghcr.io/abetlen/llama-cpp-python:latest
-            ghcr.io/abetlen/llama-cpp-python:${{ github.ref_name }}
+            ghcr.io/abetlen/llama-cpp-python:${{ env.IMAGE_TAG }}
           build-args: |
             BUILDKIT_INLINE_CACHE=1