keras-remote 0.0.1__tar.gz

keras_remote-0.0.1/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

keras_remote-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

keras_remote-0.0.1/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.4
+Name: keras-remote
+Version: 0.0.1
+Summary: Run Keras models remotely on TPU seamlessly.
+Project-URL: Homepage, https://github.com/keras-team/keras-remote
+Project-URL: Issues, https://github.com/keras-team/keras-remote/issues
+Author-email: Jeff Carpenter <code@jeffcarp.com>
+License-Expression: Apache-2.0
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.9
+Requires-Dist: cloudpickle
+Requires-Dist: keras
+Requires-Dist: numpy
+Provides-Extra: dev
+Requires-Dist: build; extra == 'dev'
+Requires-Dist: twine; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Keras Remote
+
+Run Keras models remotely on TPU as seamlessly as running the same code locally.
+
+## Prerequisites
+
+1.  **Google Cloud SDK**: Install the `gcloud` CLI.
+2.  **Authentication**: Run `gcloud auth login` and `gcloud auth application-default login`.
+3.  **Permissions**: Ensure your GCP user has permissions to create and manage TPU VMs.
+
+## Installation
+
+```bash
+pip install -r requirements.txt
+```
+
+## Running the Demo
+
+The `demo_train.py` script demonstrates how to run a Keras model on a remote TPU.
+
+```bash
+# Optional: Set your GCP project and zone
+export KERAS_REMOTE_PROJECT="your-project-id"
+export KERAS_REMOTE_ZONE="us-central1-f"  # or other zones like europe-west4-a
+
+python demo_train.py
+```
+
+**Note:** TPU availability varies by zone. If you encounter a `RESOURCE_EXHAUSTED` error, try a different zone or accelerator type (e.g., `v2-8` vs `v3-8`).
+
+The `@keras_remote.run` decorator handles:
+1.  Packaging your local code.
+2.  Provisioning (or finding) a TPU VM.
+3.  Uploading your code and dependencies.
+4.  Executing the function inside a Docker container on the TPU VM.

keras_remote-0.0.1/README.md

@@ -0,0 +1,35 @@
+# Keras Remote
+
+Run Keras models remotely on TPU as seamlessly as running the same code locally.
+
+## Prerequisites
+
+1.  **Google Cloud SDK**: Install the `gcloud` CLI.
+2.  **Authentication**: Run `gcloud auth login` and `gcloud auth application-default login`.
+3.  **Permissions**: Ensure your GCP user has permissions to create and manage TPU VMs.
+
+## Installation
+
+```bash
+pip install -r requirements.txt
+```
+
+## Running the Demo
+
+The `demo_train.py` script demonstrates how to run a Keras model on a remote TPU.
+
+```bash
+# Optional: Set your GCP project and zone
+export KERAS_REMOTE_PROJECT="your-project-id"
+export KERAS_REMOTE_ZONE="us-central1-f"  # or other zones like europe-west4-a
+
+python demo_train.py
+```
+
+**Note:** TPU availability varies by zone. If you encounter a `RESOURCE_EXHAUSTED` error, try a different zone or accelerator type (e.g., `v2-8` vs `v3-8`).
+
+The `@keras_remote.run` decorator handles:
+1.  Packaging your local code.
+2.  Provisioning (or finding) a TPU VM.
+3.  Uploading your code and dependencies.
+4.  Executing the function inside a Docker container on the TPU VM.

keras_remote-0.0.1/demo_train.py

@@ -0,0 +1,62 @@
+import os
+import socket
+
+os.environ["KERAS_BACKEND"] = "jax"
+
+import keras
+import numpy as np
+import jax
+from keras_remote import core as keras_remote
+
+
+@keras_remote.run(accelerator='v2-8')
+def train_keras_jax_model():
+  host = socket.gethostname()
+  print(f"Running on host: {host}")
+  print(f"Keras version: {keras.__version__}")
+  print(f"Keras backend: {keras.config.backend()}")
+  print(f"JAX version: {jax.__version__}")
+  print(f"JAX devices: {jax.devices()}")
+
+  num_classes = 10
+  input_shape = (28, 28, 1)
+
+  model = keras.Sequential(
+      [
+          keras.layers.Input(shape=input_shape),
+          keras.layers.Conv2D(64, kernel_size=(3, 3), activation="relu"),
+          keras.layers.Conv2D(64, kernel_size=(3, 3), activation="relu"),
+          keras.layers.MaxPooling2D(pool_size=(2, 2)),
+          keras.layers.Conv2D(128, kernel_size=(3, 3), activation="relu"),
+          keras.layers.Conv2D(128, kernel_size=(3, 3), activation="relu"),
+          keras.layers.GlobalAveragePooling2D(),
+          keras.layers.Dropout(0.5),
+          keras.layers.Dense(num_classes, activation="softmax"),
+      ]
+  )
+  print("Model defined.")
+
+  model.compile(
+      loss=keras.losses.SparseCategoricalCrossentropy(),
+      optimizer=keras.optimizers.Adam(learning_rate=1e-3),
+      metrics=[
+          keras.metrics.SparseCategoricalAccuracy(name="acc"),
+      ],
+  )
+  print("Model compiled.")
+
+  # Dummy data
+  num_samples = 128
+  x_train = np.random.rand(num_samples, *input_shape).astype(np.float32)
+  y_train = np.random.randint(0, num_classes, size=(num_samples,)).astype(np.int32)
+
+  print("Starting model.fit...")
+  model.fit(x_train, y_train, epochs=1, batch_size=32, verbose=2)
+  print("Model.fit finished.")
+
+  return f"Keras JAX training complete on {host}"
+
+if __name__ == "__main__":
+  print("Starting Keras JAX demo...")
+  result = train_keras_jax_model()
+  print(f"Demo result: {result}")

keras_remote-0.0.1/keras_remote/__init__.py

@@ -0,0 +1 @@
+from keras_remote.core import run

keras_remote-0.0.1/keras_remote/core.py

@@ -0,0 +1,95 @@
+import datetime
+import functools
+import getpass
+import inspect
+import os
+import shutil
+import tempfile
+
+from keras_remote import packager
+from keras_remote import infra
+
+logger = infra.logger
+
+def run(accelerator='v3-8', zone=None, project=None, vm_name=None):
+  def decorator(func):
+    @functools.wraps(func)
+    def wrapper(*args, **kwargs):
+      with tempfile.TemporaryDirectory() as tmpdir:
+
+        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+        context_zip_name = f'context_{timestamp}.zip'
+        remote_context_zip_path = f'/tmp/{context_zip_name}'
+
+        context_zip = os.path.join(tmpdir, context_zip_name)
+        payload_pkl = os.path.join(tmpdir, 'payload.pkl')
+        remote_runner_py = os.path.join(tmpdir, 'remote_runner.py')
+
+        # 1. Create zip/pickle artifacts
+        frame = inspect.stack()[1]
+        module = inspect.getmodule(frame[0])
+        if module:
+          caller_path = os.path.dirname(os.path.abspath(module.__file__))
+        else:
+          caller_path = os.getcwd() # Fallback
+
+        logger.info(f"Packaging directory: {caller_path}...")
+        packager.zip_working_dir(caller_path, context_zip)
+        logger.info(f"Context zip created at {context_zip}")
+
+        logger.info("Serializing payload...")
+        packager.save_payload(func, args, kwargs, payload_pkl)
+        logger.info(f"Payload pickle created at {payload_pkl}")
+
+        # Copy remote_runner.py to tmpdir
+        this_dir = os.path.dirname(os.path.abspath(__file__))
+        shutil.copy(
+            os.path.join(this_dir, "remote_runner.py"), remote_runner_py
+        )
+
+        # 2. Ensure TPU VM exists
+        if vm_name:
+          actual_vm_name = vm_name
+        else:
+          user = getpass.getuser()
+          actual_vm_name = f"remote-{user}-{accelerator}"
+        infra.ensure_tpu_vm(actual_vm_name, accelerator, zone=zone, project=project)
+
+        # 3. Upload artifacts
+        # TODO(jeffcarp): Add everything to the same zip file.
+        logger.info(f"Uploading files to {actual_vm_name}...")
+        infra.scp_to_vm(vm_name, context_zip, remote_context_zip_path, zone=zone, project=project)
+        infra.scp_to_vm(vm_name, payload_pkl, '/tmp/payload.pkl', zone=zone, project=project)
+        infra.scp_to_vm(vm_name, remote_runner_py, '/tmp/remote_runner.py', zone=zone, project=project)
+
+        # Find and upload requirements.txt
+        requirements_txt = None
+        search_dir = caller_path
+        while search_dir != "/":
+            req_path = os.path.join(search_dir, "requirements.txt")
+            if os.path.exists(req_path):
+                requirements_txt = req_path
+                break
+            parent_dir = os.path.dirname(search_dir)
+            if parent_dir == search_dir:  # Avoid infinite loop at root
+                break
+            search_dir = parent_dir
+
+        if requirements_txt:
+            logger.info(f"Using requirements.txt: {requirements_txt}")
+            infra.scp_to_vm(vm_name, requirements_txt, '/tmp/requirements.txt', zone=zone, project=project)
+            use_requirements = True
+        else:
+            logger.info("No requirements.txt found.")
+            use_requirements = False
+        logger.info("Upload complete.")
+
+        # 4. Execute remote_runner.py on the VM
+        logger.info("Executing remote script...")
+        result = infra.ssh_execute(vm_name, '/tmp/remote_runner.py', context_zip_path=remote_context_zip_path, use_requirements=use_requirements, zone=zone, project=project, accelerator_type=accelerator)
+        logger.info("Remote execution finished.")
+        # TODO: Return the deserialized result from the remote function.
+        return result
+
+    return wrapper
+  return decorator

keras_remote-0.0.1/keras_remote/infra.py

@@ -0,0 +1,180 @@
+import subprocess
+import sys
+import json
+import os
+import logging
+import shlex
+
+
+logging.basicConfig(level=logging.INFO, format='%(message)s')
+logger = logging.getLogger("keras_remote")
+
+
+def get_default_zone():
+  return os.environ.get("KERAS_REMOTE_ZONE", "us-central1-a")
+
+
+def get_default_project():
+  return os.environ.get("KERAS_REMOTE_PROJECT")
+
+
+def run_cmd(cmd, stream=False):
+  """Runs a shell command using subprocess.Popen, optionally streaming stdout."""
+  logger.info(f"Running command: {' '.join(cmd)}")
+  process = subprocess.Popen(cmd, shell=False, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+
+  if stream:
+    # Read stdout line by line
+    for line in iter(process.stdout.readline, ''):
+      if line.startswith('[REMOTE]'):
+        sys.stdout.write(line)
+        sys.stdout.flush()
+      else:
+        logger.info(line.strip())
+
+    # Read stderr after stdout is closed
+    stderr_lines = process.stderr.read()
+    if stderr_lines:
+      logger.error(f"STDERR: {stderr_lines}")
+
+  stdout, stderr = process.communicate()
+
+  if process.returncode != 0:
+    logger.error(f"Error running command: {' '.join(cmd)}")
+    if not stream:
+      logger.error(f"STDOUT: {stdout}")
+      logger.error(f"STDERR: {stderr}")
+    raise subprocess.CalledProcessError(process.returncode, cmd, output=stdout, stderr=stderr)
+
+  return stdout
+
+
+def ensure_tpu_vm(name, accelerator_type, zone=None, project=None):
+  """Ensures a TPU VM exists, creating it if necessary."""
+  if zone is None:
+    zone = get_default_zone()
+  if project is None:
+    project = get_default_project()
+
+  try:
+    list_cmd = ["gcloud", "compute", "tpus", "tpu-vm", "list", f"--zone={zone}", "--format=json"]
+    if project:
+      list_cmd.append(f"--project={project}")
+    
+    output = run_cmd(list_cmd)
+    vms = json.loads(output)
+    if any(vm['name'].endswith(name) for vm in vms):
+      logger.info(f"TPU VM {name} already exists.")
+      return
+  except subprocess.CalledProcessError:
+    logger.info(f"Failed to list TPU VMs, assuming {name} does not exist.")
+  except json.JSONDecodeError:
+    logger.info(f"Failed to parse TPU VM list output, assuming {name} does not exist.")
+
+  logger.info(f"Creating TPU VM {name}...")
+  create_cmd = [
+      "gcloud", "compute", "tpus", "tpu-vm", "create", name,
+      f"--zone={zone}",
+      f"--accelerator-type={accelerator_type}",
+      "--version=tpu-vm-base"
+  ]
+  if project:
+      create_cmd.append(f"--project={project}")
+
+  run_cmd(create_cmd, stream=True)
+  logger.info(f"TPU VM {name} created.")
+
+
+def scp_to_vm(name, local, remote, zone=None, project=None):
+  """Copies a local file to the remote VM."""
+  if zone is None:
+    zone = get_default_zone()
+  if project is None:
+    project = get_default_project()
+
+  scp_cmd = [
+      "gcloud", "compute", "tpus", "tpu-vm", "scp",
+      local, f"{name}:{remote}",
+      f"--zone={zone}", "--worker=all"
+  ]
+  if project:
+      scp_cmd.append(f"--project={project}")
+
+  run_cmd(scp_cmd)
+
+
+def get_device_count(accelerator_type):
+    """Determines the number of TPU chips (accel devices) per worker."""
+    # Heuristic: Most v2/v3/v4 TPU VMs have 4 chips (8 cores) per worker.
+    # Exceptions like v5e (litepod) can vary.
+    if "v5litepod-1" in accelerator_type:
+        return 1
+    if "v5litepod-4" in accelerator_type:
+        return 4
+    if "v5litepod-8" in accelerator_type:
+        return 8
+    # Default to 4 for v2-8, v3-8, v4-8 and their pod slices (per worker)
+    return 4
+
+
+def ssh_execute(
+    name: str,
+    python_main_file: str,
+    context_zip_path: str,
+    use_requirements: bool = False,
+    zone: str | None = None,
+    project: str | None = None,
+    accelerator_type: str = "v3-8",
+) -> None:
+  """Executes the remote script inside a Docker container on the VM."""
+  if zone is None:
+    zone = get_default_zone()
+  if project is None:
+    project = get_default_project()
+
+  docker_image = "python:3.13-slim"
+  num_devices = get_device_count(accelerator_type)
+  device_flags = " ".join([f"--device /dev/accel{i}:/dev/accel{i}" for i in range(num_devices)])
+  container_cmds = [
+      "python3 -m pip install --upgrade pip",
+  ]
+  if use_requirements:
+      container_cmds.append("python3 -m pip install -r /tmp/requirements.txt")
+
+  container_cmds.extend([
+      "python3 -m pip install jax[tpu] -f https://storage.googleapis.com/jax-releases/libtpu_releases.html",
+      f"python3 -u {python_main_file} {context_zip_path}",
+  ])
+
+  # Join commands and quote safely for bash -c
+  container_command = " && ".join(container_cmds)
+  safe_container_command = shlex.quote(container_command)
+
+  # Docker run command to be executed on the VM
+  docker_run_cmd = (
+      f"sudo docker run --rm "
+      f"-v /tmp:/tmp "
+      # Set environment variable
+      # TODO: this shouldn't be hard-coded here
+      f"-e KERAS_BACKEND=jax "
+      # Expose TPU devices to the container
+      f"{device_flags} "
+      # Often needed for TPU access
+      f"--privileged "
+      f"{docker_image} "
+      f"bash -c {safe_container_command}"
+  )
+
+  ssh_cmd = [
+      "gcloud", "compute", "tpus", "tpu-vm", "ssh", name,
+      f"--zone={zone}", "--worker=all"
+  ]
+  if project:
+      ssh_cmd.append(f"--project={project}")
+
+  ssh_cmd.append(f"--command={docker_run_cmd}")
+
+  logger.info(f"Running script inside Docker container on {name}")
+  stdout = run_cmd(ssh_cmd, stream=True)
+  # TODO: Parse stdout to extract and deserialize the function result.
+  return None

keras_remote-0.0.1/keras_remote/packager.py

@@ -0,0 +1,26 @@
+import os
+import zipfile
+import cloudpickle
+
+def zip_working_dir(base_dir, output_path):
+  """Zips the base_dir into output_path, excluding .git and __pycache__."""
+  with zipfile.ZipFile(output_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
+    for root, dirs, files in os.walk(base_dir):
+      # Exclude .git and __pycache__ directories
+      dirs[:] = [d for d in dirs if d not in ['.git', '__pycache__']]
+
+      for file in files:
+        file_path = os.path.join(root, file)
+        archive_name = os.path.relpath(file_path, base_dir)
+        zipf.write(file_path, archive_name)
+
+
+def save_payload(func, args, kwargs, output_path):
+  """Uses cloudpickle to serialize the function, args, kwargs, and dummy env_vars."""
+  payload = {
+    'func': func,
+    'args': args,
+    'kwargs': kwargs,
+  }
+  with open(output_path, 'wb') as f:
+    cloudpickle.dump(payload, f)

keras_remote-0.0.1/keras_remote/remote_runner.py

@@ -0,0 +1,55 @@
+import argparse
+import cloudpickle
+import os
+import shutil
+import sys
+import traceback
+import zipfile
+
+WORKSPACE_DIR = '/tmp/workspace'
+PAYLOAD_PKL = '/tmp/payload.pkl'
+
+def main():
+  parser = argparse.ArgumentParser()
+  parser.add_argument("context_zip", help="Path to the context zip file")
+  args = parser.parse_args()
+  context_zip_path = args.context_zip
+
+  print(f"Starting remote execution", flush=True)
+
+  # 1. Unzip context_zip_path to WORKSPACE_DIR
+  print(f"Extracting {context_zip_path} to {WORKSPACE_DIR}", flush=True)
+  os.makedirs(WORKSPACE_DIR, exist_ok=True)
+  # Clear out old workspace contents if any
+  for item in os.listdir(WORKSPACE_DIR):
+      item_path = os.path.join(WORKSPACE_DIR, item)
+      if os.path.isfile(item_path) or os.path.islink(item_path):
+          os.remove(item_path)
+      elif os.path.isdir(item_path):
+          shutil.rmtree(item_path)
+
+  with zipfile.ZipFile(context_zip_path, 'r') as zip_ref:
+    zip_ref.extractall(WORKSPACE_DIR)
+
+  # 3. Load payload.pkl
+  print(f"Loading payload from {PAYLOAD_PKL}", flush=True)
+  with open(PAYLOAD_PKL, 'rb') as f:
+    payload = cloudpickle.load(f)
+
+  func = payload['func']
+  args = payload['args']
+  kwargs = payload['kwargs']
+  # env_vars = payload['env_vars'] # Not used yet
+
+  # 4. Execute the function
+  print(f"Executing function {func.__name__}", flush=True)
+  try:
+    result = func(*args, **kwargs)
+    print(f"Function execution completed. Result: {result}", flush=True)
+    # TODO: Serialize result (e.g. base64 cloudpickle) and print to stdout for local capture.
+  except Exception as e:
+    print(f"Error during function execution:", flush=True)
+    traceback.print_exc()
+
+if __name__ == "__main__":
+  main()

keras_remote-0.0.1/pyproject.toml

@@ -0,0 +1,34 @@
+[project]
+name = "keras-remote"
+version = "0.0.1"
+authors = [
+  { name="Jeff Carpenter", email="code@jeffcarp.com" },
+]
+description = "Run Keras models remotely on TPU seamlessly."
+readme = "README.md"
+requires-python = ">=3.9"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "cloudpickle",
+    "numpy",
+    "keras",
+]
+license = "Apache-2.0"
+license-files = ["LICENCSE"]
+
+[project.optional-dependencies]
+dev = [
+    "build",
+    "twine",
+]
+
+[project.urls]
+Homepage = "https://github.com/keras-team/keras-remote"
+Issues = "https://github.com/keras-team/keras-remote/issues"
+
+[build-system]
+requires = ["hatchling >= 1.26"]
+build-backend = "hatchling.build"