skypilot-nightly 1.0.0.dev20250806__py3-none-any.whl → 1.0.0.dev20250807__py3-none-any.whl

sky/task.py

@@ -241,8 +241,8 @@ class Task:
         self,
         name: Optional[str] = None,
         *,
-        setup: Optional[str] = None,
-        run: Optional[CommandOrCommandGen] = None,
+        setup: Optional[Union[str, List[str]]] = None,
+        run: Optional[Union[CommandOrCommandGen, List[str]]] = None,
         envs: Optional[Dict[str, str]] = None,
         secrets: Optional[Dict[str, str]] = None,
         workdir: Optional[Union[str, Dict[str, Any]]] = None,
@@ -293,15 +293,15 @@ class Task:
 
         Args:
           name: A string name for the Task for display purposes.
-          setup: A setup command, which will be run before executing the run
+          setup: A setup command(s), which will be run before executing the run
             commands ``run``, and executed under ``workdir``.
           run: The actual command for the task. If not None, either a shell
-            command (str) or a command generator (callable).  If latter, it
-            must take a node rank and a list of node addresses as input and
-            return a shell command (str) (valid to return None for some nodes,
-            in which case no commands are run on them).  Run commands will be
-            run under ``workdir``. Note the command generator should be a
-            self-contained lambda.
+            command(s) (str, list(str)) or a command generator (callable). If
+            latter, it must take a node rank and a list of node addresses as
+            input and return a shell command (str) (valid to return None for
+            some nodes, in which case no commands are run on them). Run
+            commands will be run under ``workdir``. Note the command generator
+            should be a self-contained lambda.
           envs: A dictionary of environment variables to set before running the
             setup and run commands.
           secrets: A dictionary of secret environment variables to set before
@@ -347,15 +347,22 @@ class Task:
             YAML config.
         """
         self.name = name
-        self.run = run
         self.storage_mounts: Dict[str, storage_lib.Storage] = {}
         self.storage_plans: Dict[storage_lib.Storage,
                                  storage_lib.StoreType] = {}
-        self.setup = setup
         self._envs = envs or {}
         self._secrets = secrets or {}
         self._volumes = volumes or {}
 
+        # concatenate commands if given as list
+        def _concat(commands):
+            if isinstance(commands, list):
+                return '\n'.join(commands)
+            return commands
+
+        self.run = _concat(run)
+        self.setup = _concat(setup)
+
         # Validate Docker login configuration early if both envs and secrets
         # contain Docker variables
         if self._envs or self._secrets:

sky/templates/kubernetes-ray.yml.j2

@@ -777,6 +777,11 @@ available_node_types:
                 {{ ray_installation_commands }}
 
                 VIRTUAL_ENV=~/skypilot-runtime ~/.local/bin/uv pip install skypilot[kubernetes,remote]
+                # Wait for `patch` package to be installed before applying ray patches
+                until dpkg -l | grep -q "^ii  patch "; do
+                  sleep 0.1
+                  echo "Waiting for patch package to be installed..."
+                done
                 # Apply Ray patches for progress bar fix
                 ~/.local/bin/uv pip list | grep "ray " | grep 2.9.3 2>&1 > /dev/null && { 
                   VIRTUAL_ENV=~/skypilot-runtime python -c "from sky.skylet.ray_patches import patch; patch()" || exit 1; 

sky/templates/sky-serve-controller.yaml.j2

@@ -57,6 +57,7 @@ run: |
    -u -m sky.serve.service \
     --service-name {{service_name}} \
     --task-yaml {{remote_task_yaml_path}} \
+    --entrypoint {{entrypoint}} \
     {%- if consolidation_mode_job_id is not none %}
     --job-id {{consolidation_mode_job_id}} \
     {%- else %}

sky/usage/usage_lib.py

@@ -10,6 +10,8 @@ import traceback
 import typing
 from typing import Any, Callable, Dict, List, Optional, Union
 
+from typing_extensions import ParamSpec
+
 import sky
 from sky import sky_logging
 from sky.adaptors import common as adaptors_common
@@ -517,26 +519,26 @@ def entrypoint_context(name: str, fallback: bool = False):
 
 
 T = typing.TypeVar('T')
+P = ParamSpec('P')
 
 
 @typing.overload
 def entrypoint(
         name_or_fn: str,
-        fallback: bool = False
-) -> Callable[[Callable[..., T]], Callable[..., T]]:
+        fallback: bool = False) -> Callable[[Callable[P, T]], Callable[P, T]]:
     ...
 
 
 @typing.overload
-def entrypoint(name_or_fn: Callable[..., T],
-               fallback: bool = False) -> Callable[..., T]:
+def entrypoint(name_or_fn: Callable[P, T],
+               fallback: bool = False) -> Callable[P, T]:
     ...
 
 
 def entrypoint(
-    name_or_fn: Union[str, Callable[..., T]],
+    name_or_fn: Union[str, Callable[P, T]],
     fallback: bool = False
-) -> Union[Callable[..., T], Callable[[Callable[..., T]], Callable[..., T]]]:
+) -> Union[Callable[P, T], Callable[[Callable[P, T]], Callable[P, T]]]:
     return common_utils.make_decorator(entrypoint_context,
                                        name_or_fn,
                                        fallback=fallback)

sky/utils/annotations.py

@@ -1,14 +1,19 @@
 """Annotations for public APIs."""
 
 import functools
-from typing import Callable, Literal
+from typing import Callable, Literal, TypeVar
+
+from typing_extensions import ParamSpec
 
 # Whether the current process is a SkyPilot API server process.
 is_on_api_server = True
 FUNCTIONS_NEED_RELOAD_CACHE = []
 
+T = TypeVar('T')
+P = ParamSpec('P')
+
 
-def client_api(func):
+def client_api(func: Callable[P, T]) -> Callable[P, T]:
     """Mark a function as a client-side API.
 
     Code invoked by server-side functions will find annotations.is_on_api_server
@@ -38,7 +43,7 @@ def lru_cache(scope: Literal['global', 'request'], *lru_cache_args,
         lru_cache_kwargs: Keyword arguments for functools.lru_cache.
     """
 
-    def decorator(func: Callable) -> Callable:
+    def decorator(func: Callable[P, T]) -> Callable[P, T]:
         if scope == 'global':
             return functools.lru_cache(*lru_cache_args,
                                        **lru_cache_kwargs)(func)

sky/utils/common_utils.py

@@ -271,12 +271,13 @@ _current_command: Optional[str] = None
 _current_client_entrypoint: Optional[str] = None
 _using_remote_api_server: Optional[bool] = None
 _current_user: Optional['models.User'] = None
+_current_request_id: Optional[str] = None
 
 
 def set_request_context(client_entrypoint: Optional[str],
                         client_command: Optional[str],
                         using_remote_api_server: bool,
-                        user: Optional['models.User']):
+                        user: Optional['models.User'], request_id: str) -> None:
     """Override the current client entrypoint and command.
 
     This is useful when we are on the SkyPilot API server side and we have a
@@ -286,10 +287,19 @@ def set_request_context(client_entrypoint: Optional[str],
     global _current_client_entrypoint
     global _using_remote_api_server
     global _current_user
+    global _current_request_id
     _current_command = client_command
     _current_client_entrypoint = client_entrypoint
     _using_remote_api_server = using_remote_api_server
     _current_user = user
+    _current_request_id = request_id
+
+
+def get_current_request_id() -> str:
+    """Returns the current request id."""
+    if _current_request_id is not None:
+        return _current_request_id
+    return 'dummy-request-id'
 
 
 def get_current_command() -> str:

sky/utils/db/migration_utils.py

@@ -19,11 +19,11 @@ logger = sky_logging.init_logger(__name__)
 DB_INIT_LOCK_TIMEOUT_SECONDS = 10
 
 GLOBAL_USER_STATE_DB_NAME = 'state_db'
-GLOBAL_USER_STATE_VERSION = '001'
+GLOBAL_USER_STATE_VERSION = '002'
 GLOBAL_USER_STATE_LOCK_PATH = '~/.sky/locks/.state_db.lock'
 
 SPOT_JOBS_DB_NAME = 'spot_jobs_db'
-SPOT_JOBS_VERSION = '002'
+SPOT_JOBS_VERSION = '003'
 SPOT_JOBS_LOCK_PATH = '~/.sky/locks/.spot_jobs_db.lock'
 
 

{skypilot_nightly-1.0.0.dev20250806.dist-info → skypilot_nightly-1.0.0.dev20250807.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: skypilot-nightly
-Version: 1.0.0.dev20250806
+Version: 1.0.0.dev20250807
 Summary: SkyPilot: Run AI on Any Infra — Unified, Faster, Cheaper.
 Author: SkyPilot Team
 License: Apache 2.0
@@ -256,12 +256,18 @@ Dynamic: summary
 
 ----
 
-SkyPilot is an open-source framework for running AI and batch workloads on any infra.
+SkyPilot is an open-source system for running AI and batch workloads on any infra.
 
 SkyPilot **is easy to use for AI users**:
-- Quickly spin up compute on your own infra
+- Quickly spin up jobs on your own infra
 - Environment and job as code — simple and portable
-- Easy job management: queue, run, and auto-recover many jobs
+- Easy management: queue, run, and auto-recover many jobs
+
+SkyPilot **makes Kubernetes easy for AI teams**:
+
+- Slurm-like ease of use, cloud-native robustness
+- Local dev experience on K8s: SSH into pods, sync code, or connect IDE
+- Turbocharge your clusters: gang scheduling, multi-cluster, and scaling
 
 SkyPilot **unifies multiple clusters, clouds, and hardware**:
 - One interface to use reserved GPUs, Kubernetes clusters, or 16+ clouds
@@ -309,7 +315,7 @@ You can find our documentation [here](https://docs.skypilot.co/).
 
 A SkyPilot task specifies: resource requirements, data to be synced, setup commands, and the task commands.
 
-Once written in this [**unified interface**](https://docs.skypilot.co/en/latest/reference/yaml-spec.html) (YAML or Python API), the task can be launched on any available cloud.  This avoids vendor lock-in, and allows easily moving jobs to a different provider.
+Once written in this [**unified interface**](https://docs.skypilot.co/en/latest/reference/yaml-spec.html) (YAML or Python API), the task can be launched on any available infra (Kubernetes, cloud, etc.).  This avoids vendor lock-in, and allows easily moving jobs to a different provider.
 
 Paste the following into a file `my_task.yaml`:
 
@@ -347,12 +353,11 @@ sky launch my_task.yaml
 ```
 
 SkyPilot then performs the heavy-lifting for you, including:
-1. Find the lowest priced VM instance type across different clouds
-2. Provision the VM, with auto-failover if the cloud returned capacity errors
-3. Sync the local `workdir` to the VM
-4. Run the task's `setup` commands to prepare the VM for running the task
-5. Run the task's `run` commands
-
+1. Find the cheapest & available infra across your clusters or clouds
+2. Provision the GPUs (pods or VMs), with auto-failover if the infra returned capacity errors
+3. Sync your local `workdir` to the provisioned cluster
+4. Auto-install dependencies by running the task's `setup` commands
+5. Run the task's `run` commands, and stream logs
 
 See [Quickstart](https://docs.skypilot.co/en/latest/getting-started/quickstart.html) to get started with SkyPilot.
 
@@ -364,13 +369,13 @@ Latest featured examples:
 
 | Task | Examples |
 |----------|----------|
-| Training | [PyTorch](https://docs.skypilot.co/en/latest/getting-started/tutorial.html), [DeepSpeed](https://docs.skypilot.co/en/latest/examples/training/deepspeed.html), [Finetune Llama 3](https://docs.skypilot.co/en/latest/examples/training/llama-3_1-finetuning.html), [NeMo](https://docs.skypilot.co/en/latest/examples/training/nemo.html), [Ray](https://docs.skypilot.co/en/latest/examples/training/ray.html), [Unsloth](https://docs.skypilot.co/en/latest/examples/training/unsloth.html), [Jax/TPU](https://docs.skypilot.co/en/latest/examples/training/tpu.html) |
+| Training | [Verl](https://docs.skypilot.co/en/latest/examples/training/verl.html), [Finetune Llama 4](https://docs.skypilot.co/en/latest/examples/training/llama-4-finetuning.html), [PyTorch](https://docs.skypilot.co/en/latest/getting-started/tutorial.html), [DeepSpeed](https://docs.skypilot.co/en/latest/examples/training/deepspeed.html), [NeMo](https://docs.skypilot.co/en/latest/examples/training/nemo.html), [Ray](https://docs.skypilot.co/en/latest/examples/training/ray.html), [Unsloth](https://docs.skypilot.co/en/latest/examples/training/unsloth.html), [Jax/TPU](https://docs.skypilot.co/en/latest/examples/training/tpu.html) |
 | Serving | [vLLM](https://docs.skypilot.co/en/latest/examples/serving/vllm.html), [SGLang](https://docs.skypilot.co/en/latest/examples/serving/sglang.html), [Ollama](https://docs.skypilot.co/en/latest/examples/serving/ollama.html) |
 | Models | [DeepSeek-R1](https://docs.skypilot.co/en/latest/examples/models/deepseek-r1.html), [Llama 3](https://docs.skypilot.co/en/latest/examples/models/llama-3.html), [CodeLlama](https://docs.skypilot.co/en/latest/examples/models/codellama.html), [Qwen](https://docs.skypilot.co/en/latest/examples/models/qwen.html), [Mixtral](https://docs.skypilot.co/en/latest/examples/models/mixtral.html) |
 | AI apps | [RAG](https://docs.skypilot.co/en/latest/examples/applications/rag.html), [vector databases](https://docs.skypilot.co/en/latest/examples/applications/vector_database.html) (ChromaDB, CLIP) |
 | Common frameworks | [Airflow](https://docs.skypilot.co/en/latest/examples/frameworks/airflow.html), [Jupyter](https://docs.skypilot.co/en/latest/examples/frameworks/jupyter.html) |
 
-Source files and more examples can be found in [`llm/`](https://github.com/skypilot-org/skypilot/tree/master/llm) and [`examples/`](https://github.com/skypilot-org/skypilot/tree/master/examples).
+Source files can be found in [`llm/`](https://github.com/skypilot-org/skypilot/tree/master/llm) and [`examples/`](https://github.com/skypilot-org/skypilot/tree/master/examples).
 
 ## More information
 To learn more, see [SkyPilot Overview](https://docs.skypilot.co/en/latest/overview.html), [SkyPilot docs](https://docs.skypilot.co/en/latest/), and [SkyPilot blog](https://blog.skypilot.co/).