Merge branch 'ollama:main' into main

.github/workflows/release.yaml

@@ -111,13 +111,13 @@ jobs:
           - os: windows
             arch: amd64
             preset: 'CUDA 12'
-            install: https://developer.download.nvidia.com/compute/cuda/12.4.0/local_installers/cuda_12.4.0_551.61_windows.exe
-            cuda-version: '12.4'
+            install: https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_571.96_windows.exe
+            cuda-version: '12.8'
           - os: windows
             arch: amd64
             preset: 'ROCm 6'
-            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe
-            rocm-version: '6.1'
+            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe
+            rocm-version: '6.2'
     runs-on: ${{ matrix.arch == 'arm64' && format('{0}-{1}', matrix.os, matrix.arch) || matrix.os }}
     environment: release
     env:
@@ -160,6 +160,10 @@ jobs:
           echo "$hipPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
           echo "CC=$hipPath\bin\clang.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
           echo "CXX=$hipPath\bin\clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
+      - if: matrix.preset == 'CPU'
+        run: |
+          echo "CC=clang.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
+          echo "CXX=clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
       - if: ${{ !cancelled() && steps.cache-install.outputs.cache-hit != 'true' }}
         uses: actions/cache/save@v4
         with:

.github/workflows/test.yaml

@@ -81,7 +81,7 @@ jobs:
             install: https://developer.download.nvidia.com/compute/cuda/11.8.0/local_installers/cuda_11.8.0_522.06_windows.exe
             flags: '-DCMAKE_CUDA_ARCHITECTURES=87'
           - preset: ROCm
-            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q3-WinSvr2022-For-HIP.exe
+            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe
             flags: '-DAMDGPU_TARGETS=gfx1010'
     runs-on: windows
     steps:
@@ -140,6 +140,13 @@ jobs:
         env:
           CMAKE_GENERATOR: Ninja
 
+  go_mod_tidy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: check that 'go mod tidy' is clean
+        run: go mod tidy --diff || (echo "Please run 'go mod tidy'." && exit 1)
+
   test:
     strategy:
       matrix:
@@ -147,15 +154,83 @@ jobs:
     runs-on: ${{ matrix.os }}
     env:
       CGO_ENABLED: '1'
+      GOEXPERIMENT: 'synctest'
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-go@v5
+      - name: checkout
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # 4.2.2
+
+      - name: cache restore
+        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 # v4.2.0
         with:
+          # Note: unlike the other setups, this is only grabbing the mod download
+          # cache, rather than the whole mod directory, as the download cache
+          # contains zips that can be unpacked in parallel faster than they can be
+          # fetched and extracted by tar
+          path: |
+            ~/.cache/go-build
+            ~/go/pkg/mod/cache
+            ~\AppData\Local\go-build
+          # NOTE: The -3- here should be incremented when the scheme of data to be
+          # cached changes (e.g. path above changes).
+          key: ${{ github.job }}-${{ runner.os }}-${{ matrix.goarch }}-${{ matrix.buildflags }}-go-3-${{ hashFiles('**/go.sum') }}-${{ github.run_id }}
+          restore-keys: |
+            ${{ github.job }}-${{ runner.os }}-${{ matrix.goarch }}-${{ matrix.buildflags }}-go-3-${{ hashFiles('**/go.sum') }}
+            ${{ github.job }}-${{ runner.os }}-${{ matrix.goarch }}-${{ matrix.buildflags }}-go-3-
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          # The caching strategy of setup-go is less than ideal, and wastes
+          # time by not saving artifacts due to small failures like the linter
+          # complaining, etc. This means subsequent have to rebuild their world
+          # again until all checks pass. For instance, if you mispell a word,
+          # you're punished until you fix it. This is more hostile than
+          # helpful.
+          cache: false
+
           go-version-file: go.mod
+
+      # TODO(bmizerany): replace this heavy tool with just the
+      # tools/checks/binaries we want and then make them all run in parallel
+      # across jobs, not on a single tiny vm on Github Actions.
       - uses: golangci/golangci-lint-action@v6
         with:
           args: --timeout 10m0s -v
-      - run: go test ./...
+
+      - name: go test
+        # Do not skip tests in the face of linter errors, or 'go mod tidy'
+        # checks, which are secondary to the tests. Tests trump linters.
+        if: always()
+        run: go test -count=1 -benchtime=1x ./...
+
+      # It is tempting to run this in a platform independent way, but the past
+      # shows this codebase will see introductions of platform specific code
+      # generation, and so we need to check this per platform to ensure we
+      # don't abuse go generate on specific platforms.
+      - name: check that 'go generate' is clean
+        run: |
+          go generate ./...
+          git diff --name-only --exit-code || (echo "Please run 'go generate ./...'." && exit 1)
+
+      - name: cache save
+        # Always save the cache, even if the job fails. The artifacts produced
+        # during the building of test binaries are not all for naught. They can
+        # be used to speed up subsequent runs.
+        if: always()
+
+        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 # v4.2.0
+        with:
+          # Note: unlike the other setups, this is only grabbing the mod download
+          # cache, rather than the whole mod directory, as the download cache
+          # contains zips that can be unpacked in parallel faster than they can be
+          # fetched and extracted by tar
+          path: |
+            ~/.cache/go-build
+            ~/go/pkg/mod/cache
+            ~\AppData\Local\go-build
+          # NOTE: The -3- here should be incremented when the scheme of data to be
+          # cached changes (e.g. path above changes).
+          key: ${{ github.job }}-${{ runner.os }}-${{ matrix.goarch }}-${{ matrix.buildflags }}-go-3-${{ hashFiles('**/go.sum') }}-${{ github.run_id }}
 
   patches:
     runs-on: ubuntu-latest