Merge 26a490b7fc into a7f9ce9a3a

.github/actions/setup-test-environment/action.yml

@@ -57,7 +57,7 @@ runs:
         echo "Building Llama Stack"
 
         LLAMA_STACK_DIR=. \
-          uv run --no-sync llama stack build --template ci-tests --image-type venv
+          uv run llama stack show --distro ci-tests | sh
 
     - name: Configure git for commits
       shell: bash

.github/workflows/README.md

@@ -12,7 +12,7 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
 | Integration Tests (Replay) | [integration-tests.yml](integration-tests.yml) | Run the integration test suites from tests/integration in replay mode |
 | Vector IO Integration Tests | [integration-vector-io-tests.yml](integration-vector-io-tests.yml) | Run the integration test suite with various VectorIO providers |
 | Pre-commit | [pre-commit.yml](pre-commit.yml) | Run pre-commit checks |
-| Test Llama Stack Build | [providers-build.yml](providers-build.yml) | Test llama stack build |
+| Test Llama Stack Show | [providers-show.yml](providers-show.yml) | Test llama stack Show |
 | Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |
 | Integration Tests (Record) | [record-integration-tests.yml](record-integration-tests.yml) | Run the integration test suite from tests/integration |
 | Check semantic PR titles | [semantic-pr.yml](semantic-pr.yml) | Ensure that PR titles follow the conventional commit spec |

.github/workflows/integration-vector-io-tests.yml

@@ -144,7 +144,7 @@ jobs:
 
       - name: Build Llama Stack
         run: |
-          uv run --no-sync llama stack build --template ci-tests --image-type venv
+          uv run --no-sync llama stack show --distro ci-tests | sh
 
       - name: Check Storage and Memory Available Before Tests
         if: ${{ always() }}

.github/workflows/providers-build.yml

@@ -1,162 +0,0 @@
-name: Test Llama Stack Build
-
-run-name: Test llama stack build
-
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - 'llama_stack/cli/stack/build.py'
-      - 'llama_stack/cli/stack/_build.py'
-      - 'llama_stack/core/build.*'
-      - 'llama_stack/core/*.sh'
-      - '.github/workflows/providers-build.yml'
-      - 'llama_stack/distributions/**'
-      - 'pyproject.toml'
-
-  pull_request:
-    paths:
-      - 'llama_stack/cli/stack/build.py'
-      - 'llama_stack/cli/stack/_build.py'
-      - 'llama_stack/core/build.*'
-      - 'llama_stack/core/*.sh'
-      - '.github/workflows/providers-build.yml'
-      - 'llama_stack/distributions/**'
-      - 'pyproject.toml'
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  generate-matrix:
-    runs-on: ubuntu-latest
-    outputs:
-      distros: ${{ steps.set-matrix.outputs.distros }}
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
-
-      - name: Generate Distribution List
-        id: set-matrix
-        run: |
-          distros=$(ls llama_stack/distributions/*/*build.yaml | awk -F'/' '{print $(NF-1)}' | jq -R -s -c 'split("\n")[:-1]')
-          echo "distros=$distros" >> "$GITHUB_OUTPUT"
-
-  build:
-    needs: generate-matrix
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        distro: ${{ fromJson(needs.generate-matrix.outputs.distros) }}
-        image-type: [venv, container]
-      fail-fast: false # We want to run all jobs even if some fail
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
-
-      - name: Install dependencies
-        uses: ./.github/actions/setup-runner
-
-      - name: Print build dependencies
-        run: |
-          uv run llama stack build --distro ${{ matrix.distro }} --image-type ${{ matrix.image-type }} --image-name test --print-deps-only
-
-      - name: Run Llama Stack Build
-        run: |
-          # USE_COPY_NOT_MOUNT is set to true since mounting is not supported by docker buildx, we use COPY instead
-          # LLAMA_STACK_DIR is set to the current directory so we are building from the source
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --distro ${{ matrix.distro }} --image-type ${{ matrix.image-type }} --image-name test
-
-      - name: Print dependencies in the image
-        if: matrix.image-type == 'venv'
-        run: |
-          uv pip list
-
-  build-single-provider:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
-
-      - name: Install dependencies
-        uses: ./.github/actions/setup-runner
-
-      - name: Build a single provider
-        run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --image-type venv --image-name test --providers inference=remote::ollama
-
-  build-custom-container-distribution:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
-
-      - name: Install dependencies
-        uses: ./.github/actions/setup-runner
-
-      - name: Build a single provider
-        run: |
-          yq -i '.image_type = "container"' llama_stack/distributions/ci-tests/build.yaml
-          yq -i '.image_name = "test"' llama_stack/distributions/ci-tests/build.yaml
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --config llama_stack/distributions/ci-tests/build.yaml
-
-      - name: Inspect the container image entrypoint
-        run: |
-          IMAGE_ID=$(docker images --format "{{.Repository}}:{{.Tag}}" | head -n 1)
-          if [ -z "$IMAGE_ID" ]; then
-            echo "No image found"
-            exit 1
-          fi
-          entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
-          echo "Entrypoint: $entrypoint"
-          if [ "$entrypoint" != "[python -m llama_stack.core.server.server /app/run.yaml]" ]; then
-            echo "Entrypoint is not correct"
-            exit 1
-          fi
-
-  build-ubi9-container-distribution:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
-
-      - name: Install dependencies
-        uses: ./.github/actions/setup-runner
-
-      - name: Pin distribution to UBI9 base
-        run: |
-          yq -i '
-            .image_type    = "container" |
-            .image_name    = "ubi9-test" |
-            .distribution_spec.container_image = "registry.access.redhat.com/ubi9:latest"
-          ' llama_stack/distributions/ci-tests/build.yaml
-
-      - name: Build dev container (UBI9)
-        env:
-          USE_COPY_NOT_MOUNT: "true"
-          LLAMA_STACK_DIR: "."
-        run: |
-          uv run llama stack build --config llama_stack/distributions/ci-tests/build.yaml
-
-      - name: Inspect UBI9 image
-        run: |
-          IMAGE_ID=$(docker images --format "{{.Repository}}:{{.Tag}}" | head -n 1)
-          if [ -z "$IMAGE_ID" ]; then
-            echo "No image found"
-            exit 1
-          fi
-          entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
-          echo "Entrypoint: $entrypoint"
-          if [ "$entrypoint" != "[python -m llama_stack.core.server.server /app/run.yaml]" ]; then
-            echo "Entrypoint is not correct"
-            exit 1
-          fi
-
-          echo "Checking /etc/os-release in $IMAGE_ID"
-          docker run --rm --entrypoint sh "$IMAGE_ID" -c \
-              'source /etc/os-release && echo "$ID"' \
-              | grep -qE '^(rhel|ubi)$' \
-              || { echo "Base image is not UBI 9!"; exit 1; }

.github/workflows/providers-show.yml

@@ -0,0 +1,105 @@
+name: Test Llama Stack Show
+
+run-name: Test llama stack Show
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'llama_stack/cli/stack/show.py'
+      - 'llama_stack/cli/stack/_show.py'
+      - 'llama_stack/core/build.*'
+      - 'llama_stack/core/*.sh'
+      - '.github/workflows/providers-show.yml'
+      - 'llama_stack/templates/**'
+      - 'pyproject.toml'
+
+  pull_request:
+    paths:
+      - 'llama_stack/cli/stack/show.py'
+      - 'llama_stack/cli/stack/_show.py'
+      - 'llama_stack/core/build.*'
+      - 'llama_stack/core/*.sh'
+      - '.github/workflows/providers-show.yml'
+      - 'llama_stack/templates/**'
+      - 'pyproject.toml'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  generate-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      distros: ${{ steps.set-matrix.outputs.distros }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Generate Distribution List
+        id: set-matrix
+        run: |
+          distros=$(ls llama_stack/distributions/*/*build.yaml | awk -F'/' '{print $(NF-1)}' | jq -R -s -c 'split("\n")[:-1]')
+          echo "distros=$distros" >> "$GITHUB_OUTPUT"
+
+  show:
+    needs: generate-matrix
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        distro: ${{ fromJson(needs.generate-matrix.outputs.distros) }}
+        image-type: [venv, container]
+      fail-fast: false # We want to run all jobs even if some fail
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Print dependencies
+        run: |
+          uv run llama stack show --distro ${{ matrix.distro }}
+
+      - name: Install Distro using Llama Stack Show
+        run: |
+          # USE_COPY_NOT_MOUNT is set to true since mounting is not supported by docker buildx, we use COPY instead
+          # LLAMA_STACK_DIR is set to the current directory so we are building from the source
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack show --distro ${{ matrix.distro }} | sh
+
+      - name: Print dependencies in the image
+        if: matrix.image-type == 'venv'
+        run: |
+          uv pip list
+
+  show-single-provider:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Show a single provider
+        run: |
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack show --env-name test --providers inference=remote::ollama
+
+  show-from-config:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Show from Config
+        env:
+          USE_COPY_NOT_MOUNT: "true"
+          LLAMA_STACK_DIR: "."
+        run: |
+          uv run llama stack show --config llama_stack/distributions/ci-tests/build.yaml

.github/workflows/test-external.yml

@@ -44,11 +44,11 @@ jobs:
 
       - name: Print distro dependencies
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack build --config tests/external/build.yaml --print-deps-only
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack show --config tests/external/build.yaml
 
       - name: Build distro from config file
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack build --config tests/external/build.yaml
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack show --config tests/external/build.yaml | sh
 
       - name: Start Llama Stack server in background
         if: ${{ matrix.image-type }} == 'venv'

docs/source/providers/post_training/inline_torchtune-cpu.md

@@ -2,7 +2,7 @@
 
 ## Description
 
-TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.
+TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework (CPU).
 
 ## Configuration
 

docs/source/providers/post_training/inline_torchtune-gpu.md

@@ -2,7 +2,7 @@
 
 ## Description
 
-TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.
+TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework (GPU).
 
 ## Configuration
 

llama_stack/cli/stack/_show.py

@@ -0,0 +1,200 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import argparse
+import os
+import sys
+import textwrap
+from pathlib import Path
+
+import yaml
+from prompt_toolkit import prompt
+from prompt_toolkit.completion import WordCompleter
+from prompt_toolkit.validation import Validator
+from termcolor import cprint
+
+from llama_stack.cli.stack.utils import ImageType, available_templates_specs
+from llama_stack.core.build import get_provider_dependencies
+from llama_stack.core.datatypes import (
+    BuildConfig,
+    BuildProvider,
+    DistributionSpec,
+)
+from llama_stack.core.distribution import get_provider_registry
+from llama_stack.core.stack import replace_env_vars
+from llama_stack.log import get_logger
+from llama_stack.providers.datatypes import Api
+
+TEMPLATES_PATH = Path(__file__).parent.parent.parent / "templates"
+
+logger = get_logger(name=__name__, category="cli")
+
+
+# These are the dependencies needed by the distribution server.
+# `llama-stack` is automatically installed by the installation script.
+SERVER_DEPENDENCIES = [
+    "aiosqlite",
+    "fastapi",
+    "fire",
+    "httpx",
+    "uvicorn",
+    "opentelemetry-sdk",
+    "opentelemetry-exporter-otlp-proto-http",
+]
+
+
+def run_stack_show_command(args: argparse.Namespace) -> None:
+    current_venv = os.environ.get("VIRTUAL_ENV")
+    env_name = args.env_name or current_venv
+
+    if args.distro:
+        available_templates = available_templates_specs()
+        if args.distro not in available_templates:
+            cprint(
+                f"Could not find template {args.distro}. Please run `llama stack show --list-distros` to check out the available templates",
+                color="red",
+                file=sys.stderr,
+            )
+            sys.exit(1)
+        build_config = available_templates[args.distro]
+        # always venv, conda is gone and container is separate.
+        build_config.image_type = ImageType.VENV.value
+    elif args.providers:
+        provider_list: dict[str, list[BuildProvider]] = dict()
+        for api_provider in args.providers.split(","):
+            if "=" not in api_provider:
+                cprint(
+                    "Could not parse `--providers`. Please ensure the list is in the format api1=provider1,api2=provider2",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+            api, provider_type = api_provider.split("=")
+            providers_for_api = get_provider_registry().get(Api(api), None)
+            if providers_for_api is None:
+                cprint(
+                    f"{api} is not a valid API.",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+            if provider_type in providers_for_api:
+                provider = BuildProvider(
+                    provider_type=provider_type,
+                    module=None,
+                )
+                provider_list.setdefault(api, []).append(provider)
+            else:
+                cprint(
+                    f"{provider_type} is not a valid provider for the {api} API.",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+        distribution_spec = DistributionSpec(
+            providers=provider_list,
+            description=",".join(args.providers),
+        )
+        build_config = BuildConfig(image_type=ImageType.VENV.value, distribution_spec=distribution_spec)
+    elif not args.config and not args.distro:
+        name = prompt(
+            "> Enter a name for your Llama Stack (e.g. my-local-stack): ",
+            validator=Validator.from_callable(
+                lambda x: len(x) > 0,
+                error_message="Name cannot be empty, please enter a name",
+            ),
+        )
+
+        image_type = prompt(
+            "> Enter the image type you want your Llama Stack to be built as (use <TAB> to see options): ",
+            completer=WordCompleter([e.value for e in ImageType]),
+            complete_while_typing=True,
+            validator=Validator.from_callable(
+                lambda x: x in [e.value for e in ImageType],
+                error_message="Invalid image type. Use <TAB> to see options",
+            ),
+        )
+
+        env_name = f"llamastack-{name}"
+
+        cprint(
+            textwrap.dedent(
+                """
+            Llama Stack is composed of several APIs working together. Let's select
+            the provider types (implementations) you want to use for these APIs.
+            """,
+            ),
+            color="green",
+            file=sys.stderr,
+        )
+
+        cprint("Tip: use <TAB> to see options for the providers.\n", color="green", file=sys.stderr)
+
+        providers: dict[str, list[BuildProvider]] = dict()
+        for api, providers_for_api in get_provider_registry().items():
+            available_providers = [x for x in providers_for_api.keys() if x not in ("remote", "remote::sample")]
+            if not available_providers:
+                continue
+            api_provider = prompt(
+                f"> Enter provider for API {api.value}: ",
+                completer=WordCompleter(available_providers),
+                complete_while_typing=True,
+                validator=Validator.from_callable(
+                    lambda x: x in available_providers,  # noqa: B023 - see https://github.com/astral-sh/ruff/issues/7847
+                    error_message="Invalid provider, use <TAB> to see options",
+                ),
+            )
+
+            string_providers = api_provider.split(" ")
+
+            for provider in string_providers:
+                providers.setdefault(api.value, []).append(BuildProvider(provider_type=provider))
+
+        description = prompt(
+            "\n > (Optional) Enter a short description for your Llama Stack: ",
+            default="",
+        )
+
+        distribution_spec = DistributionSpec(
+            providers=providers,
+            description=description,
+        )
+
+        build_config = BuildConfig(image_type=image_type, distribution_spec=distribution_spec)
+    else:
+        with open(args.config) as f:
+            try:
+                contents = yaml.safe_load(f)
+                contents = replace_env_vars(contents)
+                build_config = BuildConfig(**contents)
+                build_config.image_type = "venv"
+            except Exception as e:
+                cprint(
+                    f"Could not parse config file {args.config}: {e}",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+
+    print(f"# Dependencies for {args.distro or args.config or env_name}")
+
+    normal_deps, special_deps, external_provider_dependencies = get_provider_dependencies(build_config)
+    normal_deps += SERVER_DEPENDENCIES
+
+    # Quote deps with commas
+    quoted_normal_deps = [quote_if_needed(dep) for dep in normal_deps]
+    print(f"uv pip install {' '.join(quoted_normal_deps)}")
+
+    for special_dep in special_deps:
+        print(f"uv pip install {quote_if_needed(special_dep)}")
+
+    for external_dep in external_provider_dependencies:
+        print(f"uv pip install {quote_if_needed(external_dep)}")
+
+
+def quote_if_needed(dep):
+    # Add quotes if the dependency contains a comma (likely version specifier)
+    return f"'{dep}'" if "," in dep else dep

llama_stack/cli/stack/build.py

@@ -1,100 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-import argparse
-import textwrap
-
-from llama_stack.cli.stack.utils import ImageType
-from llama_stack.cli.subcommand import Subcommand
-
-
-class StackBuild(Subcommand):
-    def __init__(self, subparsers: argparse._SubParsersAction):
-        super().__init__()
-        self.parser = subparsers.add_parser(
-            "build",
-            prog="llama stack build",
-            description="Build a Llama stack container",
-            formatter_class=argparse.ArgumentDefaultsHelpFormatter,
-        )
-        self._add_arguments()
-        self.parser.set_defaults(func=self._run_stack_build_command)
-
-    def _add_arguments(self):
-        self.parser.add_argument(
-            "--config",
-            type=str,
-            default=None,
-            help="Path to a config file to use for the build. You can find example configs in llama_stack.cores/**/build.yaml. If this argument is not provided, you will be prompted to enter information interactively",
-        )
-
-        self.parser.add_argument(
-            "--template",
-            type=str,
-            default=None,
-            help="""(deprecated) Name of the example template config to use for build. You may use `llama stack build --list-distros` to check out the available distributions""",
-        )
-        self.parser.add_argument(
-            "--distro",
-            "--distribution",
-            dest="distribution",
-            type=str,
-            default=None,
-            help="""Name of the distribution to use for build. You may use `llama stack build --list-distros` to check out the available distributions""",
-        )
-
-        self.parser.add_argument(
-            "--list-distros",
-            "--list-distributions",
-            action="store_true",
-            dest="list_distros",
-            default=False,
-            help="Show the available distributions for building a Llama Stack distribution",
-        )
-
-        self.parser.add_argument(
-            "--image-type",
-            type=str,
-            help="Image Type to use for the build. If not specified, will use the image type from the template config.",
-            choices=[e.value for e in ImageType],
-            default=None,  # no default so we can detect if a user specified --image-type and override image_type in the config
-        )
-
-        self.parser.add_argument(
-            "--image-name",
-            type=str,
-            help=textwrap.dedent(
-                f"""[for image-type={"|".join(e.value for e in ImageType)}] Name of the virtual environment to use for
-the build. If not specified, currently active environment will be used if found.
-            """
-            ),
-            default=None,
-        )
-        self.parser.add_argument(
-            "--print-deps-only",
-            default=False,
-            action="store_true",
-            help="Print the dependencies for the stack only, without building the stack",
-        )
-
-        self.parser.add_argument(
-            "--run",
-            action="store_true",
-            default=False,
-            help="Run the stack after building using the same image type, name, and other applicable arguments",
-        )
-        self.parser.add_argument(
-            "--providers",
-            type=str,
-            default=None,
-            help="Build a config for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple providers per API.",
-        )
-
-    def _run_stack_build_command(self, args: argparse.Namespace) -> None:
-        # always keep implementation completely silo-ed away from CLI so CLI
-        # can be fast to load and reduces dependencies
-        from ._build import run_stack_build_command
-
-        return run_stack_build_command(args)

llama_stack/cli/stack/show.py

@@ -0,0 +1,69 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+import argparse
+import textwrap
+
+from llama_stack.cli.stack.utils import ImageType
+from llama_stack.cli.subcommand import Subcommand
+
+
+class StackShow(Subcommand):
+    def __init__(self, subparsers: argparse._SubParsersAction):
+        super().__init__()
+        self.parser = subparsers.add_parser(
+            "show",
+            prog="llama stack show",
+            description="show the dependencies for a llama stack distribution",
+            formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+        )
+        self._add_arguments()
+        self.parser.set_defaults(func=self._run_stack_show_command)
+
+    def _add_arguments(self):
+        self.parser.add_argument(
+            "--config",
+            type=str,
+            default=None,
+            help="Path to a config file to use for the build. You can find example configs in llama_stack/distributions/**/build.yaml. If this argument is not provided, you will be prompted to enter information interactively",
+        )
+
+        self.parser.add_argument(
+            "--distro",
+            type=str,
+            default=None,
+            help="Name of the distro config to use for show. You may use `llama stack show --list-distros` to check out the available distros",
+        )
+
+        self.parser.add_argument(
+            "--list-distros",
+            action="store_true",
+            default=False,
+            help="Show the available templates for building a Llama Stack distribution",
+        )
+
+        self.parser.add_argument(
+            "--env-name",
+            type=str,
+            help=textwrap.dedent(
+                f"""[for image-type={"|".join(e.value for e in ImageType)}] Name of the conda or virtual environment to use for
+the build. If not specified, currently active environment will be used if found.
+            """
+            ),
+            default=None,
+        )
+        self.parser.add_argument(
+            "--providers",
+            type=str,
+            default=None,
+            help="sync dependencies for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple providers per API.",
+        )
+
+    def _run_stack_show_command(self, args: argparse.Namespace) -> None:
+        # always keep implementation completely silo-ed away from CLI so CLI
+        # can be fast to load and reduces dependencies
+        from ._show import run_stack_show_command
+
+        return run_stack_show_command(args)

llama_stack/cli/stack/stack.py

@@ -11,11 +11,11 @@ from llama_stack.cli.stack.list_stacks import StackListBuilds
 from llama_stack.cli.stack.utils import print_subcommand_description
 from llama_stack.cli.subcommand import Subcommand
 
-from .build import StackBuild
 from .list_apis import StackListApis
 from .list_providers import StackListProviders
 from .remove import StackRemove
 from .run import StackRun
+from .show import StackShow
 
 
 class StackParser(Subcommand):
@@ -39,7 +39,7 @@ class StackParser(Subcommand):
         subparsers = self.parser.add_subparsers(title="stack_subcommands")
 
         # Add sub-commands
-        StackBuild.create(subparsers)
+        StackShow.create(subparsers)
         StackListApis.create(subparsers)
         StackListProviders.create(subparsers)
         StackRun.create(subparsers)

llama_stack/cli/stack/utils.py

@@ -4,7 +4,28 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+import json
+import sys
 from enum import Enum
+from functools import lru_cache
+from pathlib import Path
+
+import yaml
+from termcolor import cprint
+
+from llama_stack.core.datatypes import (
+    BuildConfig,
+    Provider,
+    StackRunConfig,
+)
+from llama_stack.core.distribution import get_provider_registry
+from llama_stack.core.resolver import InvalidProviderError
+from llama_stack.core.utils.config_dirs import EXTERNAL_PROVIDERS_DIR
+from llama_stack.core.utils.dynamic import instantiate_class_type
+from llama_stack.core.utils.image_types import LlamaStackImageType
+from llama_stack.providers.datatypes import Api
+
+TEMPLATES_PATH = Path(__file__).parent.parent.parent / "distributions"
 
 
 class ImageType(Enum):
@@ -19,3 +40,91 @@ def print_subcommand_description(parser, subparsers):
         description = subcommand.description
         description_text += f"  {name:<21} {description}\n"
     parser.epilog = description_text
+
+
+def generate_run_config(
+    build_config: BuildConfig,
+    build_dir: Path,
+    image_name: str,
+) -> Path:
+    """
+    Generate a run.yaml template file for user to edit from a build.yaml file
+    """
+    apis = list(build_config.distribution_spec.providers.keys())
+    run_config = StackRunConfig(
+        container_image=(image_name if build_config.image_type == LlamaStackImageType.CONTAINER.value else None),
+        image_name=image_name,
+        apis=apis,
+        providers={},
+        external_providers_dir=build_config.external_providers_dir
+        if build_config.external_providers_dir
+        else EXTERNAL_PROVIDERS_DIR,
+    )
+    # build providers dict
+    provider_registry = get_provider_registry(build_config)
+    for api in apis:
+        run_config.providers[api] = []
+        providers = build_config.distribution_spec.providers[api]
+
+        for provider in providers:
+            pid = provider.provider_type.split("::")[-1]
+
+            p = provider_registry[Api(api)][provider.provider_type]
+            if p.deprecation_error:
+                raise InvalidProviderError(p.deprecation_error)
+
+            try:
+                config_type = instantiate_class_type(provider_registry[Api(api)][provider.provider_type].config_class)
+            except (ModuleNotFoundError, ValueError) as exc:
+                # HACK ALERT:
+                # This code executes after building is done, the import cannot work since the
+                # package is either available in the venv or container - not available on the host.
+                # TODO: use a "is_external" flag in ProviderSpec to check if the provider is
+                # external
+                cprint(
+                    f"Failed to import provider {provider.provider_type} for API {api} - assuming it's external, skipping: {exc}",
+                    color="yellow",
+                    file=sys.stderr,
+                )
+                # Set config_type to None to avoid UnboundLocalError
+                config_type = None
+
+            if config_type is not None and hasattr(config_type, "sample_run_config"):
+                config = config_type.sample_run_config(__distro_dir__=f"~/.llama/distributions/{image_name}")
+            else:
+                config = {}
+
+            p_spec = Provider(
+                provider_id=pid,
+                provider_type=provider.provider_type,
+                config=config,
+                module=provider.module,
+            )
+            run_config.providers[api].append(p_spec)
+
+    run_config_file = build_dir / f"{image_name}-run.yaml"
+
+    with open(run_config_file, "w") as f:
+        to_write = json.loads(run_config.model_dump_json())
+        f.write(yaml.dump(to_write, sort_keys=False))
+
+    # Only print this message for non-container builds since it will be displayed before the
+    # container is built
+    # For non-container builds, the run.yaml is generated at the very end of the build process so it
+    # makes sense to display this message
+    if build_config.image_type != LlamaStackImageType.CONTAINER.value:
+        cprint(f"You can now run your stack with `llama stack run {run_config_file}`", color="green", file=sys.stderr)
+    return run_config_file
+
+
+@lru_cache
+def available_templates_specs() -> dict[str, BuildConfig]:
+    import yaml
+
+    template_specs = {}
+    for p in TEMPLATES_PATH.rglob("*build.yaml"):
+        template_name = p.parent.name
+        with open(p) as f:
+            build_config = BuildConfig(**yaml.safe_load(f))
+            template_specs[template_name] = build_config
+    return template_specs

llama_stack/core/build.py

@@ -6,6 +6,8 @@
 
 import importlib.resources
 import sys
+import tomllib
+from pathlib import Path
 
 from pydantic import BaseModel
 from termcolor import cprint
@@ -72,8 +74,13 @@ def get_provider_dependencies(
                         external_provider_deps.append(provider_spec.module)
                     else:
                         external_provider_deps.extend(provider_spec.module)
-            if hasattr(provider_spec, "pip_packages"):
+
-                deps.extend(provider_spec.pip_packages)
+            pyproject = Path(provider_spec.module.replace(".", "/")) / "pyproject.toml"
+            with open(pyproject, "rb") as f:
+                data = tomllib.load(f)
+
+            dependencies = data.get("project", {}).get("dependencies", [])
+            deps.extend(dependencies)
             if hasattr(provider_spec, "container_image") and provider_spec.container_image:
                 raise ValueError("A stack's dependencies cannot have a container image")
 

llama_stack/providers/datatypes.py

@@ -141,7 +141,10 @@ class ProviderSpec(BaseModel):
     )
 
     is_external: bool = Field(default=False, description="Notes whether this provider is an external provider.")
-
+    package_extras: list[str] = Field(
+        default_factory=list,
+        description="Optional package extras to install when using pyproject.toml files (e.g., ['cpu', 'gpu'])",
+    )
     # used internally by the resolver; this is a hack for now
     deps__: list[str] = Field(default_factory=list)
 

llama_stack/providers/inline/agents/meta_reference/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-agents-meta-reference"
+version = "0.1.0"
+description = "Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "matplotlib",
+    "pillow",
+    "pandas",
+    "scikit-learn",
+    "mcp>=1.8.1",
+    "aiosqlite",
+    "psycopg2-binary",
+    "redis",
+    "pymongo"
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/batches/reference/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-batches-meta-reference"
+version = "0.1.0"
+description = "Meta's reference implementation of batches API with KVStore persistence."
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "openai"
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/datasetio/localfs/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-datasetio-localfs"
+version = "0.1.0"
+description = "Local filesystem-based dataset I/O provider for reading and writing datasets to local storage"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "pandas",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/eval/meta_reference/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-eval-meta-reference"
+version = "0.1.0"
+description = "Meta's reference implementation of evaluation tasks with support for multiple languages and evaluation metrics"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "tree_sitter",
+    "pythainlp",
+    "langdetect",
+    "emoji",
+    "nltk",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/files/localfs/pyproject.toml

@@ -0,0 +1,18 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-files-localfs"
+version = "0.1.0"
+description = "Local filesystem-based file storage provider for managing files and documents locally"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = []
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/inference/meta_reference/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-meta-reference"
+version = "0.1.0"
+description = "Meta's reference implementation of inference with support for various model formats and optimization techniques"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "accelerate",
+    "fairscale",
+    "torch",
+    "torchvision",
+    "transformers",
+    "zmq",
+    "lm-format-enforcer",
+    "sentence-transformers",
+    "torchao==0.8.0",
+    "fbgemm-gpu-genai==1.1.2",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/inference/sentence_transformers/pyproject.toml

@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-sentence-transformers"
+version = "0.1.0"
+description = "Sentence Transformers inference provider for text embeddings and similarity search"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "torch",
+    "torchvision",
+    "sentence-transformers",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/post_training/huggingface/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-post-training-huggingface"
+version = "0.1.0"
+description = "HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "trl",
+    "transformers",
+    "peft",
+    "datasets>=4.0.0",
+    "torch",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/post_training/torchtune/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-post-training-torchtune"
+version = "0.1.0"
+description = "TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "torchtune>=0.5.0",
+    "torchao>=0.12.0",
+    "numpy",
+]
+
+[project.optional-dependencies]
+cpu = [
+    "torch --extra-index-url https://download.pytorch.org/whl/cpu",
+]
+gpu = [
+    "torch",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/safety/code_scanner/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-safety-code-scanner"
+version = "0.1.0"
+description = "Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "codeshield",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/safety/llama_guard/pyproject.toml

@@ -0,0 +1,18 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-safety-llama-guard"
+version = "0.1.0"
+description = "Llama Guard safety provider for content moderation and safety filtering using Meta's Llama Guard model"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = []
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/safety/prompt_guard/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-safety-prompt-guard"
+version = "0.1.0"
+description = "Prompt Guard safety provider for detecting and filtering unsafe prompts and content"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "transformers[accelerate]",
+    "torch",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/scoring/basic/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-scoring-basic"
+version = "0.1.0"
+description = "Basic scoring provider for simple evaluation metrics and scoring functions"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/scoring/braintrust/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-scoring-braintrust"
+version = "0.1.0"
+description = "Braintrust scoring provider for evaluation and scoring using the Braintrust platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "autoevals",
+    "openai",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/scoring/llm_as_judge/pyproject.toml

@@ -0,0 +1,18 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-scoring-llm-as-judge"
+version = "0.1.0"
+description = "LLM-as-judge scoring provider that uses language models to evaluate and score responses"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = []
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/telemetry/meta_reference/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-telemetry-meta-reference"
+version = "0.1.0"
+description = "Meta's reference implementation of telemetry and observability using OpenTelemetry"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "opentelemetry-sdk",
+    "opentelemetry-exporter-otlp-proto-http",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/tool_runtime/rag/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-tool-runtime-rag"
+version = "0.1.0"
+description = "RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "chardet",
+    "pypdf",
+    "tqdm",
+    "numpy",
+    "scikit-learn",
+    "scipy",
+    "nltk",
+    "sentencepiece",
+    "transformers",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/vector_io/chroma/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-chroma"
+version = "0.1.0"
+description = "Chroma inline vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "chromadb",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/vector_io/faiss/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-faiss"
+version = "0.1.0"
+description = "Faiss inline vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "faiss-cpu",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/vector_io/milvus/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-milvus"
+version = "0.1.0"
+description = "Milvus inline vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "pymilvus[milvus-lite]>=2.4.10",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/vector_io/qdrant/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-qdrant"
+version = "0.1.0"
+description = "Qdrant inline vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "qdrant-client",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/inline/vector_io/sqlite_vec/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-sqlite-vec"
+version = "0.1.0"
+description = "SQLite-Vec inline vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "sqlite-vec",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/registry/agents.py

@@ -10,7 +10,6 @@ from llama_stack.providers.datatypes import (
     InlineProviderSpec,
     ProviderSpec,
 )
-from llama_stack.providers.utils.kvstore import kvstore_dependencies
 
 
 def available_providers() -> list[ProviderSpec]:
@@ -18,14 +17,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.agents,
             provider_type="inline::meta-reference",
-            pip_packages=[
-                "matplotlib",
-                "pillow",
-                "pandas",
-                "scikit-learn",
-                "mcp>=1.8.1",
-            ]
-            + kvstore_dependencies(),  # TODO make this dynamic based on the kvstore config
             module="llama_stack.providers.inline.agents.meta_reference",
             config_class="llama_stack.providers.inline.agents.meta_reference.MetaReferenceAgentsImplConfig",
             api_dependencies=[

llama_stack/providers/registry/batches.py

@@ -13,7 +13,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.batches,
             provider_type="inline::reference",
-            pip_packages=[],
             module="llama_stack.providers.inline.batches.reference",
             config_class="llama_stack.providers.inline.batches.reference.config.ReferenceBatchesImplConfig",
             api_dependencies=[

llama_stack/providers/registry/datasetio.py

@@ -18,7 +18,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.datasetio,
             provider_type="inline::localfs",
-            pip_packages=["pandas"],
             module="llama_stack.providers.inline.datasetio.localfs",
             config_class="llama_stack.providers.inline.datasetio.localfs.LocalFSDatasetIOConfig",
             api_dependencies=[],
@@ -28,9 +27,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.datasetio,
             adapter_type="huggingface",
             provider_type="remote::huggingface",
-            pip_packages=[
-                "datasets>=4.0.0",
-            ],
             module="llama_stack.providers.remote.datasetio.huggingface",
             config_class="llama_stack.providers.remote.datasetio.huggingface.HuggingfaceDatasetIOConfig",
             description="HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub.",
@@ -41,9 +37,6 @@ def available_providers() -> list[ProviderSpec]:
             provider_type="remote::nvidia",
             module="llama_stack.providers.remote.datasetio.nvidia",
             config_class="llama_stack.providers.remote.datasetio.nvidia.NvidiaDatasetIOConfig",
-            pip_packages=[
-                "datasets>=4.0.0",
-            ],
             description="NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform.",
         ),
     ]

llama_stack/providers/registry/eval.py

@@ -13,7 +13,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.eval,
             provider_type="inline::meta-reference",
-            pip_packages=["tree_sitter", "pythainlp", "langdetect", "emoji", "nltk"],
             module="llama_stack.providers.inline.eval.meta_reference",
             config_class="llama_stack.providers.inline.eval.meta_reference.MetaReferenceEvalConfig",
             api_dependencies=[
@@ -28,9 +27,6 @@ def available_providers() -> list[ProviderSpec]:
         RemoteProviderSpec(
             api=Api.eval,
             adapter_type="nvidia",
-            pip_packages=[
-                "requests",
-            ],
             provider_type="remote::nvidia",
             module="llama_stack.providers.remote.eval.nvidia",
             config_class="llama_stack.providers.remote.eval.nvidia.NVIDIAEvalConfig",

llama_stack/providers/registry/files.py

@@ -14,7 +14,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.files,
             provider_type="inline::localfs",
             # TODO: make this dynamic according to the sql store type
-            pip_packages=sql_store_pip_packages,
             module="llama_stack.providers.inline.files.localfs",
             config_class="llama_stack.providers.inline.files.localfs.config.LocalfsFilesImplConfig",
             description="Local filesystem-based file storage provider for managing files and documents locally.",

llama_stack/providers/registry/inference.py

@@ -31,7 +31,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.inference,
             provider_type="inline::meta-reference",
-            pip_packages=META_REFERENCE_DEPS,
             module="llama_stack.providers.inline.inference.meta_reference",
             config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
             description="Meta's reference implementation of inference with support for various model formats and optimization techniques.",
@@ -39,11 +38,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.inference,
             provider_type="inline::sentence-transformers",
-            # CrossEncoder depends on torchao.quantization
-            pip_packages=[
-                "torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu",
-                "sentence-transformers --no-deps",
-            ],
             module="llama_stack.providers.inline.inference.sentence_transformers",
             config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
             description="Sentence Transformers inference provider for text embeddings and similarity search.",
@@ -52,9 +46,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="cerebras",
             provider_type="remote::cerebras",
-            pip_packages=[
-                "cerebras_cloud_sdk",
-            ],
             module="llama_stack.providers.remote.inference.cerebras",
             config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
             description="Cerebras inference provider for running models on Cerebras Cloud platform.",
@@ -63,7 +54,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="ollama",
             provider_type="remote::ollama",
-            pip_packages=["ollama", "aiohttp", "h11>=0.16.0"],
             config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
             module="llama_stack.providers.remote.inference.ollama",
             description="Ollama inference provider for running local models through the Ollama runtime.",
@@ -72,7 +62,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="vllm",
             provider_type="remote::vllm",
-            pip_packages=[],
             module="llama_stack.providers.remote.inference.vllm",
             config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
             provider_data_validator="llama_stack.providers.remote.inference.vllm.VLLMProviderDataValidator",
@@ -82,7 +71,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="tgi",
             provider_type="remote::tgi",
-            pip_packages=["huggingface_hub", "aiohttp"],
             module="llama_stack.providers.remote.inference.tgi",
             config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
             description="Text Generation Inference (TGI) provider for HuggingFace model serving.",
@@ -91,7 +79,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="hf::serverless",
             provider_type="remote::hf::serverless",
-            pip_packages=["huggingface_hub", "aiohttp"],
             module="llama_stack.providers.remote.inference.tgi",
             config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
             description="HuggingFace Inference API serverless provider for on-demand model inference.",
@@ -100,7 +87,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             provider_type="remote::hf::endpoint",
             adapter_type="hf::endpoint",
-            pip_packages=["huggingface_hub", "aiohttp"],
             module="llama_stack.providers.remote.inference.tgi",
             config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
             description="HuggingFace Inference Endpoints provider for dedicated model serving.",
@@ -109,9 +95,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="fireworks",
             provider_type="remote::fireworks",
-            pip_packages=[
-                "fireworks-ai<=0.17.16",
-            ],
             module="llama_stack.providers.remote.inference.fireworks",
             config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
             provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
@@ -121,9 +104,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="together",
             provider_type="remote::together",
-            pip_packages=[
-                "together",
-            ],
             module="llama_stack.providers.remote.inference.together",
             config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
             provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
@@ -133,7 +113,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="bedrock",
             provider_type="remote::bedrock",
-            pip_packages=["boto3"],
             module="llama_stack.providers.remote.inference.bedrock",
             config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
             description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.",
@@ -142,7 +121,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="databricks",
             provider_type="remote::databricks",
-            pip_packages=[],
             module="llama_stack.providers.remote.inference.databricks",
             config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
             description="Databricks inference provider for running models on Databricks' unified analytics platform.",
@@ -151,7 +129,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="nvidia",
             provider_type="remote::nvidia",
-            pip_packages=[],
             module="llama_stack.providers.remote.inference.nvidia",
             config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
             description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.",
@@ -160,7 +137,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="runpod",
             provider_type="remote::runpod",
-            pip_packages=[],
             module="llama_stack.providers.remote.inference.runpod",
             config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
             description="RunPod inference provider for running models on RunPod's cloud GPU platform.",
@@ -169,7 +145,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="openai",
             provider_type="remote::openai",
-            pip_packages=["litellm"],
             module="llama_stack.providers.remote.inference.openai",
             config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig",
             provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
@@ -179,7 +154,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="anthropic",
             provider_type="remote::anthropic",
-            pip_packages=["litellm"],
             module="llama_stack.providers.remote.inference.anthropic",
             config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig",
             provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator",
@@ -189,9 +163,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="gemini",
             provider_type="remote::gemini",
-            pip_packages=[
-                "litellm",
-            ],
             module="llama_stack.providers.remote.inference.gemini",
             config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
             provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",
@@ -201,10 +172,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="vertexai",
             provider_type="remote::vertexai",
-            pip_packages=[
-                "litellm",
-                "google-cloud-aiplatform",
-            ],
             module="llama_stack.providers.remote.inference.vertexai",
             config_class="llama_stack.providers.remote.inference.vertexai.VertexAIConfig",
             provider_data_validator="llama_stack.providers.remote.inference.vertexai.config.VertexAIProviderDataValidator",
@@ -233,9 +200,6 @@ Available Models:
             api=Api.inference,
             adapter_type="groq",
             provider_type="remote::groq",
-            pip_packages=[
-                "litellm",
-            ],
             module="llama_stack.providers.remote.inference.groq",
             config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
             provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
@@ -245,7 +209,6 @@ Available Models:
             api=Api.inference,
             adapter_type="llama-openai-compat",
             provider_type="remote::llama-openai-compat",
-            pip_packages=["litellm"],
             module="llama_stack.providers.remote.inference.llama_openai_compat",
             config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig",
             provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
@@ -255,9 +218,6 @@ Available Models:
             api=Api.inference,
             adapter_type="sambanova",
             provider_type="remote::sambanova",
-            pip_packages=[
-                "litellm",
-            ],
             module="llama_stack.providers.remote.inference.sambanova",
             config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
             provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",
@@ -267,7 +227,6 @@ Available Models:
             api=Api.inference,
             adapter_type="passthrough",
             provider_type="remote::passthrough",
-            pip_packages=[],
             module="llama_stack.providers.remote.inference.passthrough",
             config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig",
             provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator",
@@ -277,7 +236,6 @@ Available Models:
             api=Api.inference,
             adapter_type="watsonx",
             provider_type="remote::watsonx",
-            pip_packages=["ibm_watsonx_ai"],
             module="llama_stack.providers.remote.inference.watsonx",
             config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
             provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator",
@@ -287,7 +245,6 @@ Available Models:
             api=Api.inference,
             provider_type="remote::azure",
             adapter_type="azure",
-            pip_packages=["litellm"],
             module="llama_stack.providers.remote.inference.azure",
             config_class="llama_stack.providers.remote.inference.azure.AzureConfig",
             provider_data_validator="llama_stack.providers.remote.inference.azure.config.AzureProviderDataValidator",

llama_stack/providers/registry/post_training.py

@@ -5,15 +5,12 @@
 # the root directory of this source tree.
 
 
-from typing import cast
-
 from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec
 
 # We provide two versions of these providers so that distributions can package the appropriate version of torch.
 # The CPU version is used for distributions that don't have GPU support -- they result in smaller container images.
 torchtune_def = dict(
     api=Api.post_training,
-    pip_packages=["numpy"],
     module="llama_stack.providers.inline.post_training.torchtune",
     config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
     api_dependencies=[
@@ -27,28 +24,32 @@ torchtune_def = dict(
 def available_providers() -> list[ProviderSpec]:
     return [
         InlineProviderSpec(
-            **{  # type: ignore
+            api=Api.post_training,
-                **torchtune_def,
+            provider_type="inline::torchtune-cpu",
-                "provider_type": "inline::torchtune-cpu",
+            module="llama_stack.providers.inline.post_training.torchtune",
-                "pip_packages": (
+            config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
-                    cast(list[str], torchtune_def["pip_packages"])
+            api_dependencies=[
-                    + ["torch torchtune>=0.5.0 torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu"]
+                Api.datasetio,
-                ),
+                Api.datasets,
-            },
+            ],
+            description="TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework (CPU).",
+            package_extras=["cpu"],
         ),
         InlineProviderSpec(
-            **{  # type: ignore
+            api=Api.post_training,
-                **torchtune_def,
+            provider_type="inline::torchtune-gpu",
-                "provider_type": "inline::torchtune-gpu",
+            module="llama_stack.providers.inline.post_training.torchtune",
-                "pip_packages": (
+            config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
-                    cast(list[str], torchtune_def["pip_packages"]) + ["torch torchtune>=0.5.0 torchao>=0.12.0"]
+            api_dependencies=[
-                ),
+                Api.datasetio,
-            },
+                Api.datasets,
+            ],
+            description="TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework (GPU).",
+            package_extras=["gpu"],
         ),
         InlineProviderSpec(
             api=Api.post_training,
             provider_type="inline::huggingface-gpu",
-            pip_packages=["trl", "transformers", "peft", "datasets>=4.0.0", "torch"],
             module="llama_stack.providers.inline.post_training.huggingface",
             config_class="llama_stack.providers.inline.post_training.huggingface.HuggingFacePostTrainingConfig",
             api_dependencies=[
@@ -61,7 +62,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.post_training,
             adapter_type="nvidia",
             provider_type="remote::nvidia",
-            pip_packages=["requests", "aiohttp"],
             module="llama_stack.providers.remote.post_training.nvidia",
             config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig",
             description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.",

llama_stack/providers/registry/safety.py

@@ -18,10 +18,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.safety,
             provider_type="inline::prompt-guard",
-            pip_packages=[
-                "transformers[accelerate]",
-                "torch --index-url https://download.pytorch.org/whl/cpu",
-            ],
             module="llama_stack.providers.inline.safety.prompt_guard",
             config_class="llama_stack.providers.inline.safety.prompt_guard.PromptGuardConfig",
             description="Prompt Guard safety provider for detecting and filtering unsafe prompts and content.",
@@ -29,7 +25,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.safety,
             provider_type="inline::llama-guard",
-            pip_packages=[],
             module="llama_stack.providers.inline.safety.llama_guard",
             config_class="llama_stack.providers.inline.safety.llama_guard.LlamaGuardConfig",
             api_dependencies=[
@@ -40,9 +35,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.safety,
             provider_type="inline::code-scanner",
-            pip_packages=[
-                "codeshield",
-            ],
             module="llama_stack.providers.inline.safety.code_scanner",
             config_class="llama_stack.providers.inline.safety.code_scanner.CodeScannerConfig",
             description="Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns.",
@@ -51,7 +43,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.safety,
             adapter_type="bedrock",
             provider_type="remote::bedrock",
-            pip_packages=["boto3"],
             module="llama_stack.providers.remote.safety.bedrock",
             config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig",
             description="AWS Bedrock safety provider for content moderation using AWS's safety services.",
@@ -60,7 +51,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.safety,
             adapter_type="nvidia",
             provider_type="remote::nvidia",
-            pip_packages=["requests"],
             module="llama_stack.providers.remote.safety.nvidia",
             config_class="llama_stack.providers.remote.safety.nvidia.NVIDIASafetyConfig",
             description="NVIDIA's safety provider for content moderation and safety filtering.",
@@ -69,7 +59,6 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.safety,
             adapter_type="sambanova",
             provider_type="remote::sambanova",
-            pip_packages=["litellm", "requests"],
             module="llama_stack.providers.remote.safety.sambanova",
             config_class="llama_stack.providers.remote.safety.sambanova.SambaNovaSafetyConfig",
             provider_data_validator="llama_stack.providers.remote.safety.sambanova.config.SambaNovaProviderDataValidator",

llama_stack/providers/registry/scoring.py

@@ -13,7 +13,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.scoring,
             provider_type="inline::basic",
-            pip_packages=["requests"],
             module="llama_stack.providers.inline.scoring.basic",
             config_class="llama_stack.providers.inline.scoring.basic.BasicScoringConfig",
             api_dependencies=[
@@ -25,7 +24,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.scoring,
             provider_type="inline::llm-as-judge",
-            pip_packages=[],
             module="llama_stack.providers.inline.scoring.llm_as_judge",
             config_class="llama_stack.providers.inline.scoring.llm_as_judge.LlmAsJudgeScoringConfig",
             api_dependencies=[
@@ -38,7 +36,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.scoring,
             provider_type="inline::braintrust",
-            pip_packages=["autoevals"],
             module="llama_stack.providers.inline.scoring.braintrust",
             config_class="llama_stack.providers.inline.scoring.braintrust.BraintrustScoringConfig",
             api_dependencies=[

llama_stack/providers/registry/telemetry.py

@@ -17,10 +17,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.telemetry,
             provider_type="inline::meta-reference",
-            pip_packages=[
-                "opentelemetry-sdk",
-                "opentelemetry-exporter-otlp-proto-http",
-            ],
             optional_api_dependencies=[Api.datasetio],
             module="llama_stack.providers.inline.telemetry.meta_reference",
             config_class="llama_stack.providers.inline.telemetry.meta_reference.config.TelemetryConfig",

llama_stack/providers/registry/tool_runtime.py

@@ -18,17 +18,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.tool_runtime,
             provider_type="inline::rag-runtime",
-            pip_packages=[
-                "chardet",
-                "pypdf",
-                "tqdm",
-                "numpy",
-                "scikit-learn",
-                "scipy",
-                "nltk",
-                "sentencepiece",
-                "transformers",
-            ],
             module="llama_stack.providers.inline.tool_runtime.rag",
             config_class="llama_stack.providers.inline.tool_runtime.rag.config.RagToolRuntimeConfig",
             api_dependencies=[Api.vector_io, Api.inference, Api.files],
@@ -40,7 +29,6 @@ def available_providers() -> list[ProviderSpec]:
             provider_type="remote::brave-search",
             module="llama_stack.providers.remote.tool_runtime.brave_search",
             config_class="llama_stack.providers.remote.tool_runtime.brave_search.config.BraveSearchToolConfig",
-            pip_packages=["requests"],
             provider_data_validator="llama_stack.providers.remote.tool_runtime.brave_search.BraveSearchToolProviderDataValidator",
             description="Brave Search tool for web search capabilities with privacy-focused results.",
         ),
@@ -50,7 +38,6 @@ def available_providers() -> list[ProviderSpec]:
             provider_type="remote::bing-search",
             module="llama_stack.providers.remote.tool_runtime.bing_search",
             config_class="llama_stack.providers.remote.tool_runtime.bing_search.config.BingSearchToolConfig",
-            pip_packages=["requests"],
             provider_data_validator="llama_stack.providers.remote.tool_runtime.bing_search.BingSearchToolProviderDataValidator",
             description="Bing Search tool for web search capabilities using Microsoft's search engine.",
         ),
@@ -60,7 +47,6 @@ def available_providers() -> list[ProviderSpec]:
             provider_type="remote::tavily-search",
             module="llama_stack.providers.remote.tool_runtime.tavily_search",
             config_class="llama_stack.providers.remote.tool_runtime.tavily_search.config.TavilySearchToolConfig",
-            pip_packages=["requests"],
             provider_data_validator="llama_stack.providers.remote.tool_runtime.tavily_search.TavilySearchToolProviderDataValidator",
             description="Tavily Search tool for AI-optimized web search with structured results.",
         ),
@@ -70,7 +56,6 @@ def available_providers() -> list[ProviderSpec]:
             provider_type="remote::wolfram-alpha",
             module="llama_stack.providers.remote.tool_runtime.wolfram_alpha",
             config_class="llama_stack.providers.remote.tool_runtime.wolfram_alpha.config.WolframAlphaToolConfig",
-            pip_packages=["requests"],
             provider_data_validator="llama_stack.providers.remote.tool_runtime.wolfram_alpha.WolframAlphaToolProviderDataValidator",
             description="Wolfram Alpha tool for computational knowledge and mathematical calculations.",
         ),
@@ -80,7 +65,6 @@ def available_providers() -> list[ProviderSpec]:
             provider_type="remote::model-context-protocol",
             module="llama_stack.providers.remote.tool_runtime.model_context_protocol",
             config_class="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderConfig",
-            pip_packages=["mcp>=1.8.1"],
             provider_data_validator="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderDataValidator",
             description="Model Context Protocol (MCP) tool for standardized tool calling and context management.",
         ),

llama_stack/providers/registry/vector_io.py

@@ -18,7 +18,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::meta-reference",
-            pip_packages=["faiss-cpu"],
             module="llama_stack.providers.inline.vector_io.faiss",
             config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
             deprecation_warning="Please use the `inline::faiss` provider instead.",
@@ -29,7 +28,6 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::faiss",
-            pip_packages=["faiss-cpu"],
             module="llama_stack.providers.inline.vector_io.faiss",
             config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -82,7 +80,6 @@ more details about Faiss in general.
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::sqlite-vec",
-            pip_packages=["sqlite-vec"],
             module="llama_stack.providers.inline.vector_io.sqlite_vec",
             config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -289,7 +286,6 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::sqlite_vec",
-            pip_packages=["sqlite-vec"],
             module="llama_stack.providers.inline.vector_io.sqlite_vec",
             config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
             deprecation_warning="Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.",
@@ -303,7 +299,6 @@ Please refer to the sqlite-vec provider documentation.
             api=Api.vector_io,
             adapter_type="chromadb",
             provider_type="remote::chromadb",
-            pip_packages=["chromadb-client"],
             module="llama_stack.providers.remote.vector_io.chroma",
             config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -345,7 +340,6 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::chromadb",
-            pip_packages=["chromadb"],
             module="llama_stack.providers.inline.vector_io.chroma",
             config_class="llama_stack.providers.inline.vector_io.chroma.ChromaVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -389,7 +383,6 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
             api=Api.vector_io,
             adapter_type="pgvector",
             provider_type="remote::pgvector",
-            pip_packages=["psycopg2-binary"],
             module="llama_stack.providers.remote.vector_io.pgvector",
             config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -500,7 +493,6 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
             api=Api.vector_io,
             adapter_type="weaviate",
             provider_type="remote::weaviate",
-            pip_packages=["weaviate-client"],
             module="llama_stack.providers.remote.vector_io.weaviate",
             config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig",
             provider_data_validator="llama_stack.providers.remote.vector_io.weaviate.WeaviateRequestProviderData",
@@ -541,7 +533,6 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::qdrant",
-            pip_packages=["qdrant-client"],
             module="llama_stack.providers.inline.vector_io.qdrant",
             config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -594,7 +585,6 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
             api=Api.vector_io,
             adapter_type="qdrant",
             provider_type="remote::qdrant",
-            pip_packages=["qdrant-client"],
             module="llama_stack.providers.remote.vector_io.qdrant",
             config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -607,7 +597,6 @@ Please refer to the inline provider documentation.
             api=Api.vector_io,
             adapter_type="milvus",
             provider_type="remote::milvus",
-            pip_packages=["pymilvus>=2.4.10"],
             module="llama_stack.providers.remote.vector_io.milvus",
             config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
             api_dependencies=[Api.inference],
@@ -813,7 +802,6 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::milvus",
-            pip_packages=["pymilvus[milvus-lite]>=2.4.10"],
             module="llama_stack.providers.inline.vector_io.milvus",
             config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig",
             api_dependencies=[Api.inference],

llama_stack/providers/remote/datasetio/huggingface/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-datasetio-huggingface"
+version = "0.1.0"
+description = "HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "datasets",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/datasetio/nvidia/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-datasetio-nvidia"
+version = "0.1.0"
+description = "NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "datasets",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/eval/nvidia/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-eval-nvidia"
+version = "0.1.0"
+description = "NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/files/s3/pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-files-s3"
+version = "0.1.0"
+description = "Local filesystem-based file storage provider for managing files and documents locally"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "boto3",
+    "sqlalchemy[asyncio]",
+    "aiosqlite",
+     "asyncpg",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/anthropic/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-anthropic"
+version = "0.1.0"
+description = "Anthropic inference provider for accessing Claude models and Anthropic's AI services"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/azure/pyproject.toml

@@ -0,0 +1,18 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-azure"
+version = "0.1.0"
+description = "Azure OpenAI inference provider for accessing GPT models and other Azure services. Provider documentation https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/bedrock/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-bedrock"
+version = "0.1.0"
+description = "AWS Bedrock inference provider for accessing various AI models through AWS's managed service"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "boto3",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/cerebras/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-cerebras"
+version = "0.1.0"
+description = "Cerebras inference provider for running models on Cerebras Cloud platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "cerebras_cloud_sdk",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/databricks/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-databricks"
+version = "0.1.0"
+description = "Databricks inference provider for running models on Databricks' unified analytics platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "openai",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/fireworks/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-fireworks"
+version = "0.1.0"
+description = "Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "fireworks-ai",
+    "grpcio>=1.67.1,<1.71.0",                # Pin grpcio version for compatibility
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/gemini/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-gemini"
+version = "0.1.0"
+description = "Google Gemini inference provider for accessing Gemini models and Google's AI services"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/groq/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-groq"
+version = "0.1.0"
+description = "Groq inference provider for ultra-fast inference using Groq's LPU technology"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/llama_openai_compat/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-llama-openai-compat"
+version = "0.1.0"
+description = "Llama OpenAI-compatible provider for using Llama models with OpenAI API format"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/nvidia/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-nvidia"
+version = "0.1.0"
+description = "NVIDIA inference provider for accessing NVIDIA NIM models and AI services"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "openai",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/ollama/pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-ollama"
+version = "0.1.0"
+description = "Ollama inference provider for running local models through the Ollama runtime"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "ollama",
+    "aiohttp",
+    "h11>=0.16.0",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/openai/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-openai"
+version = "0.1.0"
+description = "OpenAI inference provider for accessing GPT models and other OpenAI services"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/passthrough/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-passthrough"
+version = "0.1.0"
+description = "Passthrough inference provider for connecting to any external inference service not directly supported"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/runpod/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-runpod"
+version = "0.1.0"
+description = "RunPod inference provider for running models on RunPod's cloud GPU platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "openai",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/sambanova/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-sambanova"
+version = "0.1.0"
+description = "SambaNova inference provider for running models on SambaNova's dataflow architecture"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/tgi/pyproject.toml

@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-tgi"
+version = "0.1.0"
+description = "Text Generation Inference (TGI) provider for HuggingFace model serving"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "huggingface_hub",
+    "aiohttp",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/together/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-together"
+version = "0.1.0"
+description = "Together AI inference provider for open-source models and collaborative AI development"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "together",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/vertexai/pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-vertexai"
+version = "0.1.0"
+description = "Google VertexAI Remote Inference Provider"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+    "google-cloud-aiplatform"
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/vllm/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-vllm"
+version = "0.1.0"
+description = "Remote vLLM inference provider for connecting to vLLM servers"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "openai",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/inference/watsonx/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-inference-watsonx"
+version = "0.1.0"
+description = "IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "ibm_watson_machine_learning",
+
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/post_training/nvidia/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-post-training-nvidia"
+version = "0.1.0"
+description = "NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+    "aiohttp",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/safety/bedrock/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-safety-bedrock"
+version = "0.1.0"
+description = "AWS Bedrock safety provider for content moderation using AWS's safety services"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "boto3",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/safety/nvidia/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-safety-nvidia"
+version = "0.1.0"
+description = "NVIDIA's safety provider for content moderation and safety filtering"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/safety/sambanova/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-safety-sambanova"
+version = "0.1.0"
+description = "SambaNova's safety provider for content moderation and safety filtering"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "litellm",
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/tool_runtime/bing_search/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-tool-runtime-bing-search"
+version = "0.1.0"
+description = "Bing Search tool for web search capabilities using Microsoft's search engine"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/tool_runtime/brave_search/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-tool-runtime-brave-search"
+version = "0.1.0"
+description = "Brave Search tool for web search capabilities with privacy-focused results"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/tool_runtime/model_context_protocol/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-tool-runtime-model-context-protocol"
+version = "0.1.0"
+description = "Model Context Protocol (MCP) tool for standardized tool calling and context management"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "mcp>=1.8.1",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/tool_runtime/tavily_search/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-tool-runtime-tavily-search"
+version = "0.1.0"
+description = "Tavily Search tool for AI-optimized web search with structured results"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/tool_runtime/wolfram_alpha/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-tool-runtime-wolfram-alpha"
+version = "0.1.0"
+description = "Wolfram Alpha tool for computational knowledge and mathematical calculations"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "requests",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/vector_io/chroma/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-chroma-remote"
+version = "0.1.0"
+description = "Chroma remote vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "chromadb-client",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/vector_io/milvus/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-milvus-remote"
+version = "0.1.0"
+description = "Milvus remote vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "pymilvus>=2.4.10",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/vector_io/pgvector/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-pgvector"
+version = "0.1.0"
+description = "PGVector remote vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "psycopg2-binary",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/vector_io/qdrant/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-qdrant-remote"
+version = "0.1.0"
+description = "Qdrant remote vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "qdrant-client",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

llama_stack/providers/remote/vector_io/weaviate/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "llama-stack-provider-vector-io-weaviate"
+version = "0.1.0"
+description = "Weaviate remote vector database provider for Llama Stack"
+authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
+requires-python = ">=3.12"
+license = { "text" = "MIT" }
+dependencies = [
+    "weaviate-client",
+]
+
+
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["llama_stack*"]

tests/external/kaze.yaml

@@ -1,5 +1,5 @@
 adapter_type: kaze
-pip_packages: ["tests/external/llama-stack-provider-kaze"]
+pip_packages: ["tests/external/llama_stack_provider_kaze"]
 config_class: llama_stack_provider_kaze.config.KazeProviderConfig
 module: llama_stack_provider_kaze
 optional_api_dependencies: []

tests/unit/distribution/test_build_path.py

@@ -1,40 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from pathlib import Path
-
-from llama_stack.cli.stack._build import (
-    _run_stack_build_command_from_build_config,
-)
-from llama_stack.core.datatypes import BuildConfig, DistributionSpec
-from llama_stack.core.utils.image_types import LlamaStackImageType
-
-
-def test_container_build_passes_path(monkeypatch, tmp_path):
-    called_with = {}
-
-    def spy_build_image(build_config, image_name, distro_or_config, run_config=None):
-        called_with["path"] = distro_or_config
-        called_with["run_config"] = run_config
-        return 0
-
-    monkeypatch.setattr(
-        "llama_stack.cli.stack._build.build_image",
-        spy_build_image,
-        raising=True,
-    )
-
-    cfg = BuildConfig(
-        image_type=LlamaStackImageType.CONTAINER.value,
-        distribution_spec=DistributionSpec(providers={}, description=""),
-    )
-
-    _run_stack_build_command_from_build_config(cfg, image_name="dummy")
-
-    assert "path" in called_with
-    assert isinstance(called_with["path"], str)
-    assert Path(called_with["path"]).exists()
-    assert called_with["run_config"] is None

tests/unit/distribution/test_stack_show.py

@@ -0,0 +1,45 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import argparse
+from io import StringIO
+from unittest.mock import patch
+
+from llama_stack.cli.stack._show import (
+    run_stack_show_command,
+)
+
+
+def test_stack_show_basic():
+    args = argparse.Namespace(
+        config=None,
+        distro=None,
+        env_name="test-env",
+        providers="inference=remote::ollama",
+    )
+
+    with patch("sys.stdout", new_callable=StringIO) as mock_stdout:
+        run_stack_show_command(args)
+        output = mock_stdout.getvalue()
+
+        assert "# Dependencies for test-env" in output
+        assert "uv pip install" in output
+
+
+def test_stack_show_with_distro():
+    args = argparse.Namespace(
+        config=None,
+        distro="starter",
+        env_name=None,
+        providers=None,
+    )
+
+    with patch("sys.stdout", new_callable=StringIO) as mock_stdout:
+        run_stack_show_command(args)
+        output = mock_stdout.getvalue()
+
+        assert "# Dependencies for starter" in output
+        assert "uv pip install" in output

uv.lock

@@ -4063,27 +4063,27 @@ wheels = [
 
 [[package]]
 name = "ruff"
-version = "0.12.5"
+version = "0.9.10"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/30/cd/01015eb5034605fd98d829c5839ec2c6b4582b479707f7c1c2af861e8258/ruff-0.12.5.tar.gz", hash = "sha256:b209db6102b66f13625940b7f8c7d0f18e20039bb7f6101fbdac935c9612057e", size = 5170722, upload-time = "2025-07-24T13:26:37.456Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/20/8e/fafaa6f15c332e73425d9c44ada85360501045d5ab0b81400076aff27cf6/ruff-0.9.10.tar.gz", hash = "sha256:9bacb735d7bada9cfb0f2c227d3658fc443d90a727b47f206fb33f52f3c0eac7", size = 3759776, upload-time = "2025-03-07T15:27:44.363Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d4/de/ad2f68f0798ff15dd8c0bcc2889558970d9a685b3249565a937cd820ad34/ruff-0.12.5-py3-none-linux_armv6l.whl", hash = "sha256:1de2c887e9dec6cb31fcb9948299de5b2db38144e66403b9660c9548a67abd92", size = 11819133, upload-time = "2025-07-24T13:25:56.369Z" },
+    { url = "https://files.pythonhosted.org/packages/73/b2/af7c2cc9e438cbc19fafeec4f20bfcd72165460fe75b2b6e9a0958c8c62b/ruff-0.9.10-py3-none-linux_armv6l.whl", hash = "sha256:eb4d25532cfd9fe461acc83498361ec2e2252795b4f40b17e80692814329e42d", size = 10049494, upload-time = "2025-03-07T15:26:51.268Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/fc/c6b65cd0e7fbe60f17e7ad619dca796aa49fbca34bb9bea5f8faf1ec2643/ruff-0.12.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:d1ab65e7d8152f519e7dea4de892317c9da7a108da1c56b6a3c1d5e7cf4c5e9a", size = 12501114, upload-time = "2025-07-24T13:25:59.471Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/12/03f6dfa1b95ddd47e6969f0225d60d9d7437c91938a310835feb27927ca0/ruff-0.9.10-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:188a6638dab1aa9bb6228a7302387b2c9954e455fb25d6b4470cb0641d16759d", size = 10853584, upload-time = "2025-03-07T15:26:56.104Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/de/c6bec1dce5ead9f9e6a946ea15e8d698c35f19edc508289d70a577921b30/ruff-0.12.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:962775ed5b27c7aa3fdc0d8f4d4433deae7659ef99ea20f783d666e77338b8cf", size = 11716873, upload-time = "2025-07-24T13:26:01.496Z" },
+    { url = "https://files.pythonhosted.org/packages/02/49/1c79e0906b6ff551fb0894168763f705bf980864739572b2815ecd3c9df0/ruff-0.9.10-py3-none-macosx_11_0_arm64.whl", hash = "sha256:5284dcac6b9dbc2fcb71fdfc26a217b2ca4ede6ccd57476f52a587451ebe450d", size = 10155692, upload-time = "2025-03-07T15:27:01.385Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/16/cf372d2ebe91e4eb5b82a2275c3acfa879e0566a7ac94d331ea37b765ac8/ruff-0.12.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:73b4cae449597e7195a49eb1cdca89fd9fbb16140c7579899e87f4c85bf82f73", size = 11958829, upload-time = "2025-07-24T13:26:03.721Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/01/85e8082e41585e0e1ceb11e41c054e9e36fed45f4b210991052d8a75089f/ruff-0.9.10-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:47678f39fa2a3da62724851107f438c8229a3470f533894b5568a39b40029c0c", size = 10369760, upload-time = "2025-03-07T15:27:04.023Z" },
-    { url = "https://files.pythonhosted.org/packages/25/bf/cd07e8f6a3a6ec746c62556b4c4b79eeb9b0328b362bb8431b7b8afd3856/ruff-0.12.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8b13489c3dc50de5e2d40110c0cce371e00186b880842e245186ca862bf9a1ac", size = 11626619, upload-time = "2025-07-24T13:26:06.118Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/90/0bc60bd4e5db051f12445046d0c85cc2c617095c0904f1aa81067dc64aea/ruff-0.9.10-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:99713a6e2766b7a17147b309e8c915b32b07a25c9efd12ada79f217c9c778b3e", size = 9912196, upload-time = "2025-03-07T15:27:06.93Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/c9/c2ccb3b8cbb5661ffda6925f81a13edbb786e623876141b04919d1128370/ruff-0.12.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f1504fea81461cf4841778b3ef0a078757602a3b3ea4b008feb1308cb3f23e08", size = 13221894, upload-time = "2025-07-24T13:26:08.292Z" },
+    { url = "https://files.pythonhosted.org/packages/66/ea/0b7e8c42b1ec608033c4d5a02939c82097ddcb0b3e393e4238584b7054ab/ruff-0.9.10-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:524ee184d92f7c7304aa568e2db20f50c32d1d0caa235d8ddf10497566ea1a12", size = 11434985, upload-time = "2025-03-07T15:27:10.082Z" },
-    { url = "https://files.pythonhosted.org/packages/6b/58/68a5be2c8e5590ecdad922b2bcd5583af19ba648f7648f95c51c3c1eca81/ruff-0.12.5-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:c7da4129016ae26c32dfcbd5b671fe652b5ab7fc40095d80dcff78175e7eddd4", size = 14163909, upload-time = "2025-07-24T13:26:10.474Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/86/3171d1eff893db4f91755175a6e1163c5887be1f1e2f4f6c0c59527c2bfd/ruff-0.9.10-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:df92aeac30af821f9acf819fc01b4afc3dfb829d2782884f8739fb52a8119a16", size = 12155842, upload-time = "2025-03-07T15:27:12.727Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/d1/ef6b19622009ba8386fdb792c0743f709cf917b0b2f1400589cbe4739a33/ruff-0.12.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ca972c80f7ebcfd8af75a0f18b17c42d9f1ef203d163669150453f50ca98ab7b", size = 13583652, upload-time = "2025-07-24T13:26:13.381Z" },
+    { url = "https://files.pythonhosted.org/packages/89/9e/700ca289f172a38eb0bca752056d0a42637fa17b81649b9331786cb791d7/ruff-0.9.10-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:de42e4edc296f520bb84954eb992a07a0ec5a02fecb834498415908469854a52", size = 11613804, upload-time = "2025-03-07T15:27:15.944Z" },
-    { url = "https://files.pythonhosted.org/packages/62/e3/1c98c566fe6809a0c83751d825a03727f242cdbe0d142c9e292725585521/ruff-0.12.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8dbbf9f25dfb501f4237ae7501d6364b76a01341c6f1b2cd6764fe449124bb2a", size = 12700451, upload-time = "2025-07-24T13:26:15.488Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/92/648020b3b5db180f41a931a68b1c8575cca3e63cec86fd26807422a0dbad/ruff-0.9.10-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d257f95b65806104b6b1ffca0ea53f4ef98454036df65b1eda3693534813ecd1", size = 13823776, upload-time = "2025-03-07T15:27:18.996Z" },
-    { url = "https://files.pythonhosted.org/packages/24/ff/96058f6506aac0fbc0d0fc0d60b0d0bd746240a0594657a2d94ad28033ba/ruff-0.12.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c47dea6ae39421851685141ba9734767f960113d51e83fd7bb9958d5be8763a", size = 12937465, upload-time = "2025-07-24T13:26:17.808Z" },
+    { url = "https://files.pythonhosted.org/packages/5e/a6/cc472161cd04d30a09d5c90698696b70c169eeba2c41030344194242db45/ruff-0.9.10-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b60dec7201c0b10d6d11be00e8f2dbb6f40ef1828ee75ed739923799513db24c", size = 11302673, upload-time = "2025-03-07T15:27:21.655Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/d3/68bc5e7ab96c94b3589d1789f2dd6dd4b27b263310019529ac9be1e8f31b/ruff-0.12.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:c5076aa0e61e30f848846f0265c873c249d4b558105b221be1828f9f79903dc5", size = 11771136, upload-time = "2025-07-24T13:26:20.422Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/db/d31c361c4025b1b9102b4d032c70a69adb9ee6fde093f6c3bf29f831c85c/ruff-0.9.10-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:d838b60007da7a39c046fcdd317293d10b845001f38bcb55ba766c3875b01e43", size = 10235358, upload-time = "2025-03-07T15:27:24.72Z" },
-    { url = "https://files.pythonhosted.org/packages/52/75/7356af30a14584981cabfefcf6106dea98cec9a7af4acb5daaf4b114845f/ruff-0.12.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:a5a4c7830dadd3d8c39b1cc85386e2c1e62344f20766be6f173c22fb5f72f293", size = 11601644, upload-time = "2025-07-24T13:26:22.928Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/86/d6374e24a14d4d93ebe120f45edd82ad7dcf3ef999ffc92b197d81cdc2a5/ruff-0.9.10-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:ccaf903108b899beb8e09a63ffae5869057ab649c1e9231c05ae354ebc62066c", size = 9886177, upload-time = "2025-03-07T15:27:27.282Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/67/91c71d27205871737cae11025ee2b098f512104e26ffd8656fd93d0ada0a/ruff-0.12.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:46699f73c2b5b137b9dc0fc1a190b43e35b008b398c6066ea1350cce6326adcb", size = 12478068, upload-time = "2025-07-24T13:26:26.134Z" },
+    { url = "https://files.pythonhosted.org/packages/00/62/a61691f6eaaac1e945a1f3f59f1eea9a218513139d5b6c2b8f88b43b5b8f/ruff-0.9.10-py3-none-musllinux_1_2_i686.whl", hash = "sha256:f9567d135265d46e59d62dc60c0bfad10e9a6822e231f5b24032dba5a55be6b5", size = 10864747, upload-time = "2025-03-07T15:27:30.637Z" },
-    { url = "https://files.pythonhosted.org/packages/34/04/b6b00383cf2f48e8e78e14eb258942fdf2a9bf0287fbf5cdd398b749193a/ruff-0.12.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:5a655a0a0d396f0f072faafc18ebd59adde8ca85fb848dc1b0d9f024b9c4d3bb", size = 12991537, upload-time = "2025-07-24T13:26:28.533Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/94/2c7065e1d92a8a8a46d46d9c3cf07b0aa7e0a1e0153d74baa5e6620b4102/ruff-0.9.10-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:5f202f0d93738c28a89f8ed9eaba01b7be339e5d8d642c994347eaa81c6d75b8", size = 11360441, upload-time = "2025-03-07T15:27:33.356Z" },
-    { url = "https://files.pythonhosted.org/packages/3e/b9/053d6445dc7544fb6594785056d8ece61daae7214859ada4a152ad56b6e0/ruff-0.12.5-py3-none-win32.whl", hash = "sha256:dfeb2627c459b0b78ca2bbdc38dd11cc9a0a88bf91db982058b26ce41714ffa9", size = 11751575, upload-time = "2025-07-24T13:26:30.835Z" },
+    { url = "https://files.pythonhosted.org/packages/a7/8f/1f545ea6f9fcd7bf4368551fb91d2064d8f0577b3079bb3f0ae5779fb773/ruff-0.9.10-py3-none-win32.whl", hash = "sha256:bfb834e87c916521ce46b1788fbb8484966e5113c02df216680102e9eb960029", size = 10247401, upload-time = "2025-03-07T15:27:35.994Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/0f/ab16e8259493137598b9149734fec2e06fdeda9837e6f634f5c4e35916da/ruff-0.12.5-py3-none-win_amd64.whl", hash = "sha256:ae0d90cf5f49466c954991b9d8b953bd093c32c27608e409ae3564c63c5306a5", size = 12882273, upload-time = "2025-07-24T13:26:32.929Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/18/fb703603ab108e5c165f52f5b86ee2aa9be43bb781703ec87c66a5f5d604/ruff-0.9.10-py3-none-win_amd64.whl", hash = "sha256:f2160eeef3031bf4b17df74e307d4c5fb689a6f3a26a2de3f7ef4044e3c484f1", size = 11366360, upload-time = "2025-03-07T15:27:38.66Z" },
-    { url = "https://files.pythonhosted.org/packages/00/db/c376b0661c24cf770cb8815268190668ec1330eba8374a126ceef8c72d55/ruff-0.12.5-py3-none-win_arm64.whl", hash = "sha256:48cdbfc633de2c5c37d9f090ba3b352d1576b0015bfc3bc98eaf230275b7e805", size = 11951564, upload-time = "2025-07-24T13:26:34.994Z" },
+    { url = "https://files.pythonhosted.org/packages/35/85/338e603dc68e7d9994d5d84f24adbf69bae760ba5efd3e20f5ff2cec18da/ruff-0.9.10-py3-none-win_arm64.whl", hash = "sha256:5fd804c0327a5e5ea26615550e706942f348b197d5475ff34c19733aee4b2e69", size = 10436892, upload-time = "2025-03-07T15:27:41.687Z" },
 ]
 
 [[package]]