skypilot-nightly 1.0.0.dev20250804__py3-none-any.whl → 1.0.0.dev20250807__py3-none-any.whl

sky/utils/rich_utils.py

@@ -15,11 +15,13 @@ from sky.utils import message_utils
 from sky.utils import rich_console_utils
 
 if typing.TYPE_CHECKING:
+    import aiohttp
     import requests
     import rich.console as rich_console
 else:
     requests = adaptors_common.LazyImport('requests')
     rich_console = adaptors_common.LazyImport('rich.console')
+    aiohttp = adaptors_common.LazyImport('aiohttp')
 
 GeneralStatus = Union['rich_console.Status', 'EncodedStatus']
 
@@ -398,3 +400,121 @@ def decode_rich_status(
     finally:
         if decoding_status is not None:
             decoding_status.__exit__(None, None, None)
+
+
+async def decode_rich_status_async(
+        response: 'aiohttp.ClientResponse'
+) -> typing.AsyncIterator[Optional[str]]:
+    """Async version of rich_utils.decode_rich_status that decodes rich status
+    messages from an aiohttp response.
+
+    Args:
+        response: The aiohttp response.
+
+    Yields:
+        Optional[str]: Decoded lines or None for control messages.
+    """
+    decoding_status = None
+    try:
+        last_line = ''
+        # Buffer to store incomplete UTF-8 bytes between chunks
+        undecoded_buffer = b''
+
+        # Iterate over the response content in chunks
+        async for chunk in response.content.iter_chunked(8192):
+            if chunk is None:
+                return
+
+            # Append the new chunk to any leftover bytes from previous iteration
+            current_bytes = undecoded_buffer + chunk
+            undecoded_buffer = b''
+
+            # Try to decode the combined bytes
+            try:
+                encoded_msg = current_bytes.decode('utf-8')
+            except UnicodeDecodeError as e:
+                # Check if this is potentially an incomplete sequence at the end
+                if e.start > 0:
+                    # Decode the valid part
+                    encoded_msg = current_bytes[:e.start].decode('utf-8')
+
+                    # Check if the remaining bytes are likely a partial char
+                    # or actually invalid UTF-8
+                    remaining_bytes = current_bytes[e.start:]
+                    if len(remaining_bytes) < 4:  # Max UTF-8 char is 4 bytes
+                        # Likely incomplete - save for next chunk
+                        undecoded_buffer = remaining_bytes
+                    else:
+                        # Likely invalid - replace with replacement character
+                        encoded_msg += remaining_bytes.decode('utf-8',
+                                                              errors='replace')
+                        undecoded_buffer = b''
+                else:
+                    # Error at the very beginning of the buffer - invalid UTF-8
+                    encoded_msg = current_bytes.decode('utf-8',
+                                                       errors='replace')
+                    undecoded_buffer = b''
+
+            lines = encoded_msg.splitlines(keepends=True)
+
+            # Skip processing if lines is empty to avoid IndexError
+            if not lines:
+                continue
+
+            lines[0] = last_line + lines[0]
+            last_line = lines[-1]
+            # If the last line is not ended with `\r` or `\n` (with ending
+            # spaces stripped), it means the last line is not a complete line.
+            # We keep the last line in the buffer and continue.
+            if (not last_line.strip(' ').endswith('\r') and
+                    not last_line.strip(' ').endswith('\n')):
+                lines = lines[:-1]
+            else:
+                # Reset the buffer for the next line, as the last line is a
+                # complete line.
+                last_line = ''
+
+            for line in lines:
+                if line.endswith('\r\n'):
+                    # Replace `\r\n` with `\n`, as printing a line ends with
+                    # `\r\n` in linux will cause the line to be empty.
+                    line = line[:-2] + '\n'
+                is_payload, line = message_utils.decode_payload(
+                    line, raise_for_mismatch=False)
+                control = None
+                if is_payload:
+                    control, encoded_status = Control.decode(line)
+                if control is None:
+                    yield line
+                    continue
+
+                if control == Control.RETRY:
+                    raise exceptions.RequestInterruptedError(
+                        'Streaming interrupted. Please retry.')
+                # control is not None, i.e. it is a rich status control message.
+                # In async context, we'll handle rich status controls normally
+                # since async typically runs in main thread
+                if control == Control.INIT:
+                    decoding_status = client_status(encoded_status)
+                else:
+                    if decoding_status is None:
+                        # status may not be initialized if a user use --tail for
+                        # sky api logs.
+                        continue
+                    assert decoding_status is not None, (
+                        f'Rich status not initialized: {line}')
+                    if control == Control.UPDATE:
+                        decoding_status.update(encoded_status)
+                    elif control == Control.STOP:
+                        decoding_status.stop()
+                    elif control == Control.EXIT:
+                        decoding_status.__exit__(None, None, None)
+                    elif control == Control.START:
+                        decoding_status.start()
+                    elif control == Control.HEARTBEAT:
+                        # Heartbeat is not displayed to the user, so we do not
+                        # need to update the status.
+                        pass
+    finally:
+        if decoding_status is not None:
+            decoding_status.__exit__(None, None, None)

{skypilot_nightly-1.0.0.dev20250804.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.dev20250804
+Version: 1.0.0.dev20250807
 Summary: SkyPilot: Run AI on Any Infra — Unified, Faster, Cheaper.
 Author: SkyPilot Team
 License: Apache 2.0
@@ -57,6 +57,7 @@ Requires-Dist: pyjwt
 Requires-Dist: gitpython
 Requires-Dist: types-paramiko
 Requires-Dist: alembic
+Requires-Dist: aiohttp
 Provides-Extra: aws
 Requires-Dist: awscli>=1.27.10; extra == "aws"
 Requires-Dist: botocore>=1.29.10; extra == "aws"
@@ -132,6 +133,7 @@ Requires-Dist: casbin; extra == "server"
 Requires-Dist: sqlalchemy_adapter; extra == "server"
 Requires-Dist: passlib; extra == "server"
 Requires-Dist: pyjwt; extra == "server"
+Requires-Dist: aiohttp; extra == "server"
 Provides-Extra: all
 Requires-Dist: awscli>=1.27.10; extra == "all"
 Requires-Dist: botocore>=1.29.10; extra == "all"
@@ -186,6 +188,7 @@ Requires-Dist: casbin; extra == "all"
 Requires-Dist: sqlalchemy_adapter; extra == "all"
 Requires-Dist: passlib; extra == "all"
 Requires-Dist: pyjwt; extra == "all"
+Requires-Dist: aiohttp; extra == "all"
 Dynamic: author
 Dynamic: classifier
 Dynamic: description
@@ -235,6 +238,7 @@ Dynamic: summary
 ----
 
 :fire: *News* :fire:
+- [Aug 2025] Run and serve **OpenAI GPT-OSS models** (gpt-oss-120b, gpt-oss-20b) with one command on any infra: [**example**](./llm/gpt-oss/)
 - [Jul 2025] Run distributed **RL training for LLMs** with Verl (PPO, GRPO) on any cloud: [**example**](./llm/verl/)
 - [Jul 2025] 🎉 SkyPilot v0.10.0 released! [**blog post**](https://blog.skypilot.co/announcing-skypilot-0.10.0/), [**release notes**](https://github.com/skypilot-org/skypilot/releases/tag/v0.10.0)
 - [Jul 2025] Finetune **Llama4** on any distributed cluster/cloud: [**example**](./llm/llama-4-finetuning/)
@@ -252,12 +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
@@ -305,7 +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`:
 
@@ -343,12 +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.
 
@@ -360,13 +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/).