Merge branch 'master' of github.com:skypilot-org/skypilot into fast-j…

…ob-submission

.github/workflows/format.yml

@@ -21,29 +21,35 @@ jobs:
         python-version: ["3.8"]
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+    - name: Install the latest version of uv
+      uses: astral-sh/setup-uv@v4
       with:
+        version: "latest"
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install yapf==0.32.0
-        pip install toml==0.10.2
-        pip install black==22.10.0
-        pip install isort==5.12.0
+        uv venv --seed ~/test-env
+        source ~/test-env/bin/activate
+        uv pip install yapf==0.32.0
+        uv pip install toml==0.10.2
+        uv pip install black==22.10.0
+        uv pip install isort==5.12.0
     - name: Running yapf
       run: |
+        source ~/test-env/bin/activate
         yapf --diff --recursive ./ --exclude 'sky/skylet/ray_patches/**' \
             --exclude 'sky/skylet/providers/ibm/**'
     - name: Running black
       run: |
+        source ~/test-env/bin/activate
         black --diff --check sky/skylet/providers/ibm/
     - name: Running isort for black formatted files
       run: |
+        source ~/test-env/bin/activate
         isort --diff --check --profile black -l 88 -m 3 \
             sky/skylet/providers/ibm/
     - name: Running isort for yapf formatted files
       run: |
+        source ~/test-env/bin/activate
         isort --diff --check ./ --sg 'sky/skylet/ray_patches/**' \
             --sg 'sky/skylet/providers/ibm/**'

.github/workflows/mypy.yml

@@ -11,6 +11,8 @@ on:
     branches:
       - master
       - 'releases/**'
+  merge_group:
+
 jobs:
   mypy:
     runs-on: ubuntu-latest
@@ -19,15 +21,18 @@ jobs:
         python-version: ["3.8"]
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+    - name: Install the latest version of uv
+      uses: astral-sh/setup-uv@v4
       with:
+        version: "latest"
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install mypy==$(grep mypy requirements-dev.txt | cut -d'=' -f3)
-        pip install $(grep types- requirements-dev.txt | tr '\n' ' ')
+        uv venv --seed ~/test-env
+        source ~/test-env/bin/activate
+        uv pip install mypy==$(grep mypy requirements-dev.txt | cut -d'=' -f3)
+        uv pip install $(grep types- requirements-dev.txt | tr '\n' ' ')
     - name: Running mypy
       run: |
+        source ~/test-env/bin/activate
         mypy $(cat tests/mypy_files.txt)

.github/workflows/pylint.yml

@@ -21,16 +21,20 @@ jobs:
         python-version: ["3.8"]
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+    - name: Install the latest version of uv
+      uses: astral-sh/setup-uv@v4
       with:
+        version: "latest"
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install ".[all]"
-        pip install pylint==2.14.5
-        pip install pylint-quotes==0.2.3
+        uv venv --seed ~/test-env
+        source ~/test-env/bin/activate
+        uv pip install --prerelease=allow "azure-cli>=2.65.0"
+        uv pip install ".[all]"
+        uv pip install pylint==2.14.5
+        uv pip install pylint-quotes==0.2.3
     - name: Analysing the code with pylint
       run: |
+        source ~/test-env/bin/activate
         pylint --load-plugins pylint_quotes sky

.github/workflows/pytest.yml

@@ -35,26 +35,21 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
-
-      - name: Install Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      - name: Install the latest version of uv
+        uses: astral-sh/setup-uv@v4
         with:
+          version: "latest"
           python-version: ${{ matrix.python-version }}
-
-      - name: Cache dependencies
-        uses: actions/cache@v3
-        if: startsWith(runner.os, 'Linux')
-        with:
-          path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-pytest-${{ matrix.python-version }}
-          restore-keys: |
-            ${{ runner.os }}-pip-pytest-${{ matrix.python-version }}
-
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
-          pip install -e ".[all]"
-          pip install pytest pytest-xdist pytest-env>=0.6 memory-profiler==0.61.0
-
+          uv venv --seed ~/test-env
+          source ~/test-env/bin/activate
+          uv pip install --prerelease=allow "azure-cli>=2.65.0"
+          # Use -e to include examples and tests folder in the path for unit
+          # tests to access them.
+          uv pip install -e ".[all]"
+          uv pip install pytest pytest-xdist pytest-env>=0.6 memory-profiler==0.61.0
       - name: Run tests with pytest
-        run: SKYPILOT_DISABLE_USAGE_COLLECTION=1 SKYPILOT_SKIP_CLOUD_IDENTITY_CHECK=1 pytest -n 0 --dist no ${{ matrix.test-path }}
+        run: |
+          source ~/test-env/bin/activate
+          SKYPILOT_DISABLE_USAGE_COLLECTION=1 SKYPILOT_SKIP_CLOUD_IDENTITY_CHECK=1 pytest -n 0 --dist no ${{ matrix.test-path }}

.github/workflows/test-doc-build.yml

@@ -14,24 +14,28 @@ on:
   merge_group:
 
 jobs:
-  format:
+  doc-build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.10"]
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+    - name: Install the latest version of uv
+      uses: astral-sh/setup-uv@v4
       with:
+        version: "latest"
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install .
+        uv venv --seed ~/test-env
+        source ~/test-env/bin/activate
+        uv pip install --prerelease=allow "azure-cli>=2.65.0"
+        uv pip install ".[all]"
         cd docs
-        pip install -r ./requirements-docs.txt
+        uv pip install -r ./requirements-docs.txt
     - name: Build documentation
       run: |
+        source ~/test-env/bin/activate
         cd ./docs
         ./build.sh

.pre-commit-config.yaml

@@ -0,0 +1,74 @@
+# Ensure this configuration aligns with format.sh and requirements.txt
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+
+-   repo: https://github.com/psf/black
+    rev: 22.10.0  # Match the version from requirements
+    hooks:
+    -   id: black
+        name: black (IBM specific)
+        files: "^sky/skylet/providers/ibm/.*"  # Match only files in the IBM directory
+
+-   repo: https://github.com/pycqa/isort
+    rev: 5.12.0  # Match the version from requirements
+    hooks:
+    # First isort command
+    -   id: isort
+        name: isort (general)
+        args:
+          - "--sg=build/**"  # Matches "${ISORT_YAPF_EXCLUDES[@]}"
+          - "--sg=sky/skylet/providers/ibm/**"
+        files: "^(sky|tests|examples|llm|docs)/.*"  # Only match these directories
+    # Second isort command
+    -   id: isort
+        name: isort (IBM specific)
+        args:
+          - "--profile=black"
+          - "-l=88"
+          - "-m=3"
+        files: "^sky/skylet/providers/ibm/.*"  # Only match IBM-specific directory
+
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.991  # Match the version from requirements
+    hooks:
+    -   id: mypy
+        args:
+            # From tests/mypy_files.txt
+            - "sky"
+            - "--exclude"
+            - "sky/benchmark|sky/callbacks|sky/skylet/providers/azure|sky/resources.py|sky/backends/monkey_patches"
+        pass_filenames: false
+        additional_dependencies:
+            - types-PyYAML
+            - types-requests<2.31  # Match the condition in requirements.txt
+            - types-setuptools
+            - types-cachetools
+            - types-pyvmomi
+
+-   repo: https://github.com/google/yapf
+    rev: v0.32.0  # Match the version from requirements
+    hooks:
+    -   id: yapf
+        name: yapf
+        exclude: (build/.*|sky/skylet/providers/ibm/.*)  # Matches exclusions from the script
+        args: ['--recursive', '--parallel']  # Only necessary flags
+        additional_dependencies: [toml==0.10.2]
+
+-   repo: https://github.com/pylint-dev/pylint
+    rev: v2.14.5  # Match the version from requirements
+    hooks:
+    -   id: pylint
+        additional_dependencies:
+            - pylint-quotes==0.2.3  # Match the version from requirements
+        name: pylint
+        args:
+            - --rcfile=.pylintrc  # Use your custom pylint configuration
+            - --load-plugins=pylint_quotes  # Load the pylint-quotes plugin
+        files: ^sky/  # Only include files from the 'sky/' directory
+        exclude: ^sky/skylet/providers/ibm/

CONTRIBUTING.md

@@ -1,7 +1,7 @@
 # Contributing to SkyPilot
 
-Thank you for your interest in contributing to SkyPilot! We welcome and value 
-all contributions to the project, including but not limited to: 
+Thank you for your interest in contributing to SkyPilot! We welcome and value
+all contributions to the project, including but not limited to:
 
 * [Bug reports](https://github.com/skypilot-org/skypilot/issues) and [discussions](https://github.com/skypilot-org/skypilot/discussions)
 * [Pull requests](https://github.com/skypilot-org/skypilot/pulls) for bug fixes and new features
@@ -26,7 +26,7 @@ pip install -r requirements-dev.txt
 ### Testing
 To run smoke tests (NOTE: Running all smoke tests launches ~20 clusters):
 ```
-# Run all tests except for AWS and Lambda Cloud
+# Run all tests on AWS and Azure (default smoke test clouds)
 pytest tests/test_smoke.py
 
 # Terminate a test's cluster even if the test failed (default is to keep it around for debugging)
@@ -41,11 +41,11 @@ pytest tests/test_smoke.py::test_minimal
 # Only run managed spot tests
 pytest tests/test_smoke.py --managed-spot
 
-# Only run test for AWS + generic tests
-pytest tests/test_smoke.py --aws
+# Only run test for GCP + generic tests
+pytest tests/test_smoke.py --gcp
 
-# Change cloud for generic tests to aws
-pytest tests/test_smoke.py --generic-cloud aws
+# Change cloud for generic tests to Azure
+pytest tests/test_smoke.py --generic-cloud azure
 ```
 
 For profiling code, use:
@@ -78,6 +78,7 @@ It has some convenience features which you might find helpful (see [Dockerfile](
 - If relevant, add tests for your changes. For changes that touch the core system, run the [smoke tests](#testing) and ensure they pass.
 - Follow the [Google style guide](https://google.github.io/styleguide/pyguide.html).
 - Ensure code is properly formatted by running [`format.sh`](https://github.com/skypilot-org/skypilot/blob/master/format.sh).
+  - [Optional] You can also install pre-commit hooks by running `pre-commit install` to automatically format your code on commit.
 - Push your changes to your fork and open a pull request in the SkyPilot repository.
 - In the PR description, write a `Tested:` section to describe relevant tests performed.
 

Dockerfile_k8s

@@ -7,7 +7,7 @@ ARG DEBIAN_FRONTEND=noninteractive
 
 # Initialize conda for root user, install ssh and other local dependencies
 RUN apt update -y && \
-    apt install git gcc rsync sudo patch openssh-server pciutils nano fuse socat netcat curl -y && \
+    apt install git gcc rsync sudo patch openssh-server pciutils nano fuse socat netcat-openbsd curl -y && \
     rm -rf /var/lib/apt/lists/* && \
     apt remove -y python3 && \
     conda init

Dockerfile_k8s_gpu

@@ -7,7 +7,7 @@ ARG DEBIAN_FRONTEND=noninteractive
 # We remove cuda lists to avoid conflicts with the cuda version installed by ray
 RUN rm -rf /etc/apt/sources.list.d/cuda* && \
     apt update -y && \
-    apt install git gcc rsync sudo patch openssh-server pciutils nano fuse unzip socat netcat curl -y && \
+    apt install git gcc rsync sudo patch openssh-server pciutils nano fuse unzip socat netcat-openbsd curl -y && \
     rm -rf /var/lib/apt/lists/*
 
 # Setup SSH and generate hostkeys
@@ -36,6 +36,7 @@ SHELL ["/bin/bash", "-c"]
 
 # Install conda and other dependencies
 # Keep the conda and Ray versions below in sync with the ones in skylet.constants
+# Keep this section in sync with the custom image optimization recommendations in our docs (kubernetes-getting-started.rst)
 RUN curl https://repo.anaconda.com/miniconda/Miniconda3-py310_23.11.0-2-Linux-x86_64.sh -o Miniconda3-Linux-x86_64.sh && \
     bash Miniconda3-Linux-x86_64.sh -b && \
     eval "$(~/miniconda3/bin/conda shell.bash hook)" && conda init && conda config --set auto_activate_base true && conda activate base && \

README.md

@@ -155,10 +155,11 @@ SkyPilot then performs the heavy-lifting for you, including:
 Refer to [Quickstart](https://skypilot.readthedocs.io/en/latest/getting-started/quickstart.html) to get started with SkyPilot.
 
 ## More Information
-To learn more, see our [documentation](https://skypilot.readthedocs.io/en/latest/), [blog](https://blog.skypilot.co/), and [community integrations](https://blog.skypilot.co/community/).
+To learn more, see [Concept: Sky Computing](https://docs.skypilot.co/en/latest/sky-computing.html), [SkyPilot docs](https://skypilot.readthedocs.io/en/latest/), and [SkyPilot blog](https://blog.skypilot.co/).
 
 <!-- Keep this section in sync with index.rst in SkyPilot Docs -->
 Runnable examples:
+- [**AI Gallery**](https://docs.skypilot.co/en/latest/gallery/index.html)
 - LLMs on SkyPilot
   - [Llama 3.2: lightweight and vision models](./llm/llama-3_2/)
   - [Pixtral](./llm/pixtral/)
@@ -183,7 +184,7 @@ Runnable examples:
   - [LocalGPT](./llm/localgpt)
   - [Falcon](./llm/falcon)
   - Add yours here & see more in [`llm/`](./llm)!
-- Framework examples: [PyTorch DDP](https://github.com/skypilot-org/skypilot/blob/master/examples/resnet_distributed_torch.yaml), [DeepSpeed](./examples/deepspeed-multinode/sky.yaml), [JAX/Flax on TPU](https://github.com/skypilot-org/skypilot/blob/master/examples/tpu/tpuvm_mnist.yaml), [Stable Diffusion](https://github.com/skypilot-org/skypilot/tree/master/examples/stable_diffusion), [Detectron2](https://github.com/skypilot-org/skypilot/blob/master/examples/detectron2_docker.yaml), [Distributed](https://github.com/skypilot-org/skypilot/blob/master/examples/resnet_distributed_tf_app.py) [TensorFlow](https://github.com/skypilot-org/skypilot/blob/master/examples/resnet_app_storage.yaml), [Ray Train](examples/distributed_ray_train/ray_train.yaml), [NeMo](https://github.com/skypilot-org/skypilot/blob/master/examples/nemo/nemo.yaml), [programmatic grid search](https://github.com/skypilot-org/skypilot/blob/master/examples/huggingface_glue_imdb_grid_search_app.py), [Docker](https://github.com/skypilot-org/skypilot/blob/master/examples/docker/echo_app.yaml), [Cog](https://github.com/skypilot-org/skypilot/blob/master/examples/cog/), [Unsloth](https://github.com/skypilot-org/skypilot/blob/master/examples/unsloth/unsloth.yaml), [Ollama](https://github.com/skypilot-org/skypilot/blob/master/llm/ollama), [llm.c](https://github.com/skypilot-org/skypilot/tree/master/llm/gpt-2), [Airflow](./examples/airflow/training_workflow) and [many more (`examples/`)](./examples).
+- Framework examples: [PyTorch DDP](https://github.com/skypilot-org/skypilot/blob/master/examples/resnet_distributed_torch.yaml), [DeepSpeed](./examples/deepspeed-multinode/sky.yaml), [JAX/Flax on TPU](https://github.com/skypilot-org/skypilot/blob/master/examples/tpu/tpuvm_mnist.yaml), [Stable Diffusion](https://github.com/skypilot-org/skypilot/tree/master/examples/stable_diffusion), [Detectron2](https://github.com/skypilot-org/skypilot/blob/master/examples/detectron2_docker.yaml), [Distributed](https://github.com/skypilot-org/skypilot/blob/master/examples/resnet_distributed_tf_app.py) [TensorFlow](https://github.com/skypilot-org/skypilot/blob/master/examples/resnet_app_storage.yaml), [Ray Train](examples/distributed_ray_train/ray_train.yaml), [NeMo](https://github.com/skypilot-org/skypilot/blob/master/examples/nemo/), [programmatic grid search](https://github.com/skypilot-org/skypilot/blob/master/examples/huggingface_glue_imdb_grid_search_app.py), [Docker](https://github.com/skypilot-org/skypilot/blob/master/examples/docker/echo_app.yaml), [Cog](https://github.com/skypilot-org/skypilot/blob/master/examples/cog/), [Unsloth](https://github.com/skypilot-org/skypilot/blob/master/examples/unsloth/unsloth.yaml), [Ollama](https://github.com/skypilot-org/skypilot/blob/master/llm/ollama), [llm.c](https://github.com/skypilot-org/skypilot/tree/master/llm/gpt-2), [Airflow](./examples/airflow/training_workflow) and [many more (`examples/`)](./examples).
 
 Case Studies and Integrations: [Community Spotlights](https://blog.skypilot.co/community/)
 

docs/source/_static/custom.js

@@ -7,7 +7,7 @@ document.addEventListener('DOMContentLoaded', function () {
        script.setAttribute('data-project-logo', 'https://avatars.githubusercontent.com/u/109387420?s=100&v=4');
        script.setAttribute('data-modal-disclaimer', 'Results are automatically generated and may be inaccurate or contain inappropriate information. Do not include any sensitive information in your query.\n**To get further assistance, you can chat directly with the development team** by joining the [SkyPilot Slack](https://slack.skypilot.co/).');
        script.setAttribute('data-modal-title', 'SkyPilot Docs AI - Ask a Question.');
-       script.setAttribute('data-button-position-bottom', '85px');
+       script.setAttribute('data-button-position-bottom', '100px');
        script.async = true;
        document.head.appendChild(script);
 });
@@ -25,14 +25,14 @@ document.addEventListener('DOMContentLoaded', function () {
 document.addEventListener('DOMContentLoaded', () => {
     // New items:
     const newItems = [
-        { selector: '.caption-text', text: 'SkyServe: Model Serving' },
         { selector: '.toctree-l1 > a', text: 'Managed Jobs' },
         { selector: '.toctree-l1 > a', text: 'Pixtral (Mistral AI)' },
         { selector: '.toctree-l1 > a', text: 'Many Parallel Jobs' },
         { selector: '.toctree-l1 > a', text: 'Reserved, Capacity Blocks, DWS' },
         { selector: '.toctree-l1 > a', text: 'Llama 3.2 (Meta)' },
         { selector: '.toctree-l1 > a', text: 'Admin Policy Enforcement' },
         { selector: '.toctree-l1 > a', text: 'Using Existing Machines' },
+        { selector: '.toctree-l1 > a', text: 'Concept: Sky Computing' },
     ];
     newItems.forEach(({ selector, text }) => {
         document.querySelectorAll(selector).forEach((el) => {