Merge branch 'master' into gpt-fast-mixtral-moe

Author: agunapal

.github/workflows/regression_tests_cpu_binaries.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, macOS-latest]
+        os: [ubuntu-20.04, macos-latest]
         python-version: ["3.8", "3.9", "3.10"]
         binaries: ["pypi", "conda"]
         exclude:
@@ -31,38 +31,33 @@ jobs:
         with:
           submodules: recursive
       - name: Setup conda with Python ${{ matrix.python-version }}
-        if: matrix.os == 'macos-14'
         uses: conda-incubator/setup-miniconda@v3
         with:
           auto-update-conda: true
           channels: anaconda, conda-forge
           python-version: ${{ matrix.python-version }}
-      - name: Setup conda with Python ${{ matrix.python-version }}
-        if: matrix.os != 'macos-14'
-        uses: s-weigand/setup-conda@v1
-        with:
-          update-conda: true
-          python-version: ${{ matrix.python-version }}
-          conda-channels: anaconda, conda-forge
       - name: Setup Java 17
         uses: actions/setup-java@v3
         with:
           distribution: 'zulu'
           java-version: '17'
       - name: Checkout TorchServe
         uses: actions/checkout@v3
-      - name: Run install dependencies and regression test
-        if: matrix.os == 'macos-14'
-        shell: bash -el {0}
-        run: |
-          conda info
-          python ts_scripts/install_dependencies.py --environment=dev
-          python test/regression_tests.py --binaries --${{ matrix.binaries }} --nightly
       - name: Install dependencies
-        if: matrix.os != 'macos-14'
+        shell: bash -el {0}
         run: |
+          echo "=====CHECK ENV AND PYTHON VERSION===="
+          conda info --envs
+          python --version
+          echo "=====RUN INSTALL DEPENDENCIES===="
           python ts_scripts/install_dependencies.py --environment=dev
-      - name: Validate Torchserve CPU Regression
-        if: matrix.os != 'macos-14'
+      - name: Torchserve Regression Tests
+        shell: bash -el {0}
+        env:
+          TS_MAC_ARM64_CPU_ONLY: ${{ matrix.os == 'macos-latest' && 'True' || 'False' }}
         run: |
+          echo "=====CHECK ENV AND PYTHON VERSION===="
+          conda info --envs
+          python --version
+          echo "=====RUN REGRESSION TESTS===="
           python test/regression_tests.py --binaries --${{ matrix.binaries }} --nightly

.github/workflows/regression_tests_gpu_binaries.yml

@@ -39,12 +39,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           architecture: x64
-      - name: Setup Conda
-        uses: s-weigand/setup-conda@v1
-        with:
-          update-conda: true
-          python-version: ${{ matrix.python-version }}
-          conda-channels: anaconda, conda-forge
+      - run: python --version
       - run: conda --version
       - name: Setup Java 17
         uses: actions/setup-java@v3
@@ -53,17 +48,17 @@ jobs:
           java-version: '17'
       - name: Install dependencies
         shell: bash -el {0}
-        run: | 
+        run: |
           echo "=====CHECK ENV AND PYTHON VERSION===="
           /home/ubuntu/actions-runner/_work/serve/serve/3/condabin/conda info --envs
           python --version
           echo "=====RUN INSTALL DEPENDENCIES===="
           python ts_scripts/install_dependencies.py --environment=dev --cuda=cu121
       - name: Torchserve Regression Tests
-        shell: bash -el {0}  
+        shell: bash -el {0}
         run: |
           echo "=====CHECK ENV AND PYTHON VERSION===="
           /home/ubuntu/actions-runner/_work/serve/serve/3/condabin/conda info --envs
           python --version
           echo "=====RUN REGRESSION TESTS===="
-          python test/regression_tests.py --binaries --${{ matrix.binaries }} --nightly
+          python test/regression_tests.py --binaries --${{ matrix.binaries }} --nightly

test/pytest/test_continuous_batching.py

@@ -94,6 +94,7 @@ def register_model(mar_file_path, model_store, torchserve):
     test_utils.unregister_model(model_name)
 
 
+@pytest.mark.skip(reason="Skipping this test for now")
 def test_echo_stream_inference(model_name_and_stdout):
     model_name, _ = model_name_and_stdout
     responses = []
@@ -145,6 +146,7 @@ def test_echo_stream_inference(model_name_and_stdout):
     assert all_predictions[3] == "When travelling to NYC, I was able to"
 
 
+@pytest.mark.skip(reason="Skipping this test for now")
 def test_decoding_stage(monkeypatch):
     monkeypatch.syspath_prepend((CURR_FILE_PATH / "test_data" / "streaming"))
 
@@ -211,6 +213,7 @@ def test_decoding_stage(monkeypatch):
     assert ctx.cache["id2"]["encoded"]["attention_mask"].size()[-1] == 11
 
 
+@pytest.mark.skip(reason="Skipping this test for now")
 def test_closed_connection(model_name_and_stdout):
     model_name, stdout = model_name_and_stdout