cjm-torch-plugin-utils 0.0.1__tar.gz

cjm_torch_plugin_utils-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 2022, fastai
+
+   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.

cjm_torch_plugin_utils-0.0.1/MANIFEST.in

@@ -0,0 +1,5 @@
+include pyproject.toml
+include LICENSE
+include CONTRIBUTING.md
+include README.md
+recursive-exclude * __pycache__

cjm_torch_plugin_utils-0.0.1/PKG-INFO

@@ -0,0 +1,165 @@
+Metadata-Version: 2.4
+Name: cjm-torch-plugin-utils
+Version: 0.0.1
+Summary: PyTorch helpers for cjm-plugin-system plugins: GPU memory release, typed CUDA-OOM handling, and device selection.
+Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cj-mills/cjm-torch-plugin-utils
+Project-URL: Documentation, https://cj-mills.github.io/cjm-torch-plugin-utils/
+Keywords: nbdev
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm-plugin-system>=0.0.37
+Requires-Dist: numpy
+Requires-Dist: torch
+Dynamic: license-file
+
+# cjm-torch-plugin-utils
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_torch_plugin_utils
+```
+
+## Project Structure
+
+    nbs/
+    ├── device.ipynb # Resolve a device spec ("auto" / "cpu" / "cuda" / "cuda:N") to a concrete torch device string.
+    ├── memory.ipynb # Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for releasing models, factored out of the per-plugin reimplementations.
+    └── oom.ipynb    # Convert torch CUDA out-of-memory exceptions into the substrate's typed `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict and reload.
+
+Total: 3 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    device["device<br/>Device resolution"]
+    memory["memory<br/>GPU model release"]
+    oom["oom<br/>CUDA OOM handling"]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### Device resolution (`device.ipynb`)
+
+> Resolve a device spec (“auto” / “cpu” / “cuda” / “cuda:N”) to a
+> concrete torch device string.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.device import (
+    resolve_torch_device
+)
+```
+
+#### Functions
+
+``` python
+def resolve_torch_device(
+    spec: str = "auto",  # Requested device: "auto", "cpu", "cuda", or "cuda:N"
+) -> str:                # Concrete device string
+    """
+    Resolve a device spec to a concrete torch device string.
+    
+    `"auto"` resolves to `"cuda"` when CUDA is available, else `"cpu"`. Any
+    explicit spec (`"cpu"`, `"cuda"`, `"cuda:0"`, ...) is returned unchanged.
+    """
+```
+
+### GPU model release (`memory.ipynb`)
+
+> Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for
+> releasing models, factored out of the per-plugin reimplementations.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.memory import (
+    release_model
+)
+```
+
+#### Functions
+
+``` python
+def release_model(
+    obj: Any,                     # The plugin instance holding the model attribute(s)
+    model_attr_names: List[str],  # Names of the attributes to release, in release order
+    device: str = "cuda",         # Device the model is on; gates the CUDA-specific cleanup
+    *,
+    logger: logging.Logger,       # Logger for best-effort failure reporting
+) -> None
+    """
+    Release one or more model objects: move to CPU, drop references, gc, free CUDA cache.
+    
+    For each name in `model_attr_names`, if `obj` has a non-None attribute:
+      1. when on CUDA, best-effort `.to('cpu')` (frees GPU tensors; skipped for
+         objects without a `.to` method, e.g. processors/tokenizers),
+      2. `setattr(obj, name, None)` and drop the local reference.
+    Then a single `gc.collect()` and — on CUDA — `empty_cache()` + `synchronize()`.
+    
+    Best-effort throughout: failures are logged and swallowed. Missing or
+    already-None attributes are skipped, so the call is idempotent.
+    """
+```
+
+### CUDA OOM handling (`oom.ipynb`)
+
+> Convert torch CUDA out-of-memory exceptions into the substrate’s typed
+> `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict
+> and reload.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.oom import (
+    cuda_oom_to_plugin_resource_error
+)
+```
+
+#### Functions
+
+``` python
+def cuda_oom_to_plugin_resource_error(
+    exc: BaseException,          # The caught CUDA OOM exception (e.g. torch.cuda.OutOfMemoryError)
+    *,
+    label: str,                  # Context for the message, e.g. "loading model 'X'" or "inference"
+    headroom_mb: float = 100.0,  # Best-effort margin added to `available` to estimate `needed`
+) -> PluginResourceError:        # Typed error for the substrate's CR-7 reactive-retry path
+    """
+    Convert a CUDA out-of-memory exception into a substrate-typed `PluginResourceError`.
+    
+    SG-47 Track B: a plugin's GPU inference / model-load site catches
+    `torch.cuda.OutOfMemoryError` and re-raises the result of this helper so the
+    substrate sees a typed resource error (evict + reload + retry via CR-7)
+    instead of an opaque crash.
+    
+    `needed` is a best-effort estimate (`available + headroom_mb`): the true
+    required VRAM is unknowable from the exception, and CR-7 triggers eviction
+    regardless of magnitude, so an approximation above `available` is sufficient.
+    
+    The caller raises the returned error, preserving the original cause:
+    
+        try:
+            model = Model.from_pretrained(repo_id, ...)
+        except torch.cuda.OutOfMemoryError as e:
+            raise cuda_oom_to_plugin_resource_error(e, label=f"loading {repo_id!r}") from e
+    """
+```

cjm_torch_plugin_utils-0.0.1/README.md

@@ -0,0 +1,146 @@
+# cjm-torch-plugin-utils
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_torch_plugin_utils
+```
+
+## Project Structure
+
+    nbs/
+    ├── device.ipynb # Resolve a device spec ("auto" / "cpu" / "cuda" / "cuda:N") to a concrete torch device string.
+    ├── memory.ipynb # Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for releasing models, factored out of the per-plugin reimplementations.
+    └── oom.ipynb    # Convert torch CUDA out-of-memory exceptions into the substrate's typed `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict and reload.
+
+Total: 3 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    device["device<br/>Device resolution"]
+    memory["memory<br/>GPU model release"]
+    oom["oom<br/>CUDA OOM handling"]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### Device resolution (`device.ipynb`)
+
+> Resolve a device spec (“auto” / “cpu” / “cuda” / “cuda:N”) to a
+> concrete torch device string.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.device import (
+    resolve_torch_device
+)
+```
+
+#### Functions
+
+``` python
+def resolve_torch_device(
+    spec: str = "auto",  # Requested device: "auto", "cpu", "cuda", or "cuda:N"
+) -> str:                # Concrete device string
+    """
+    Resolve a device spec to a concrete torch device string.
+    
+    `"auto"` resolves to `"cuda"` when CUDA is available, else `"cpu"`. Any
+    explicit spec (`"cpu"`, `"cuda"`, `"cuda:0"`, ...) is returned unchanged.
+    """
+```
+
+### GPU model release (`memory.ipynb`)
+
+> Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for
+> releasing models, factored out of the per-plugin reimplementations.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.memory import (
+    release_model
+)
+```
+
+#### Functions
+
+``` python
+def release_model(
+    obj: Any,                     # The plugin instance holding the model attribute(s)
+    model_attr_names: List[str],  # Names of the attributes to release, in release order
+    device: str = "cuda",         # Device the model is on; gates the CUDA-specific cleanup
+    *,
+    logger: logging.Logger,       # Logger for best-effort failure reporting
+) -> None
+    """
+    Release one or more model objects: move to CPU, drop references, gc, free CUDA cache.
+    
+    For each name in `model_attr_names`, if `obj` has a non-None attribute:
+      1. when on CUDA, best-effort `.to('cpu')` (frees GPU tensors; skipped for
+         objects without a `.to` method, e.g. processors/tokenizers),
+      2. `setattr(obj, name, None)` and drop the local reference.
+    Then a single `gc.collect()` and — on CUDA — `empty_cache()` + `synchronize()`.
+    
+    Best-effort throughout: failures are logged and swallowed. Missing or
+    already-None attributes are skipped, so the call is idempotent.
+    """
+```
+
+### CUDA OOM handling (`oom.ipynb`)
+
+> Convert torch CUDA out-of-memory exceptions into the substrate’s typed
+> `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict
+> and reload.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.oom import (
+    cuda_oom_to_plugin_resource_error
+)
+```
+
+#### Functions
+
+``` python
+def cuda_oom_to_plugin_resource_error(
+    exc: BaseException,          # The caught CUDA OOM exception (e.g. torch.cuda.OutOfMemoryError)
+    *,
+    label: str,                  # Context for the message, e.g. "loading model 'X'" or "inference"
+    headroom_mb: float = 100.0,  # Best-effort margin added to `available` to estimate `needed`
+) -> PluginResourceError:        # Typed error for the substrate's CR-7 reactive-retry path
+    """
+    Convert a CUDA out-of-memory exception into a substrate-typed `PluginResourceError`.
+    
+    SG-47 Track B: a plugin's GPU inference / model-load site catches
+    `torch.cuda.OutOfMemoryError` and re-raises the result of this helper so the
+    substrate sees a typed resource error (evict + reload + retry via CR-7)
+    instead of an opaque crash.
+    
+    `needed` is a best-effort estimate (`available + headroom_mb`): the true
+    required VRAM is unknowable from the exception, and CR-7 triggers eviction
+    regardless of magnitude, so an approximation above `available` is sufficient.
+    
+    The caller raises the returned error, preserving the original cause:
+    
+        try:
+            model = Model.from_pretrained(repo_id, ...)
+        except torch.cuda.OutOfMemoryError as e:
+            raise cuda_oom_to_plugin_resource_error(e, label=f"loading {repo_id!r}") from e
+    """
+```

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils/_modidx.py

@@ -0,0 +1,13 @@
+# Autogenerated by nbdev
+
+d = { 'settings': { 'branch': 'main',
+                'doc_baseurl': '/cjm-torch-plugin-utils',
+                'doc_host': 'https://cj-mills.github.io',
+                'git_url': 'https://github.com/cj-mills/cjm-torch-plugin-utils',
+                'lib_path': 'cjm_torch_plugin_utils'},
+  'syms': { 'cjm_torch_plugin_utils.device': { 'cjm_torch_plugin_utils.device.resolve_torch_device': ( 'device.html#resolve_torch_device',
+                                                                                                       'cjm_torch_plugin_utils/device.py')},
+            'cjm_torch_plugin_utils.memory': { 'cjm_torch_plugin_utils.memory.release_model': ( 'memory.html#release_model',
+                                                                                                'cjm_torch_plugin_utils/memory.py')},
+            'cjm_torch_plugin_utils.oom': { 'cjm_torch_plugin_utils.oom.cuda_oom_to_plugin_resource_error': ( 'oom.html#cuda_oom_to_plugin_resource_error',
+                                                                                                              'cjm_torch_plugin_utils/oom.py')}}}

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils/device.py

@@ -0,0 +1,24 @@
+"""Resolve a device spec ("auto" / "cpu" / "cuda" / "cuda:N") to a concrete torch device string.
+
+Docs: https://cj-mills.github.io/cjm-torch-plugin-utilsdevice.html.md"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/device.ipynb.
+
+# %% auto #0
+__all__ = ['resolve_torch_device']
+
+# %% ../nbs/device.ipynb #exports
+import torch
+
+# %% ../nbs/device.ipynb #resolve-device
+def resolve_torch_device(
+    spec: str = "auto",  # Requested device: "auto", "cpu", "cuda", or "cuda:N"
+) -> str:                # Concrete device string
+    """Resolve a device spec to a concrete torch device string.
+
+    `"auto"` resolves to `"cuda"` when CUDA is available, else `"cpu"`. Any
+    explicit spec (`"cpu"`, `"cuda"`, `"cuda:0"`, ...) is returned unchanged.
+    """
+    if spec != "auto":
+        return spec
+    return "cuda" if torch.cuda.is_available() else "cpu"

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils/memory.py

@@ -0,0 +1,55 @@
+"""Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for releasing models, factored out of the per-plugin reimplementations.
+
+Docs: https://cj-mills.github.io/cjm-torch-plugin-utilsmemory.html.md"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/memory.ipynb.
+
+# %% auto #0
+__all__ = ['release_model']
+
+# %% ../nbs/memory.ipynb #exports
+import gc
+import logging
+from typing import Any, List
+
+import torch
+
+# %% ../nbs/memory.ipynb #release-model
+def release_model(
+    obj: Any,                     # The plugin instance holding the model attribute(s)
+    model_attr_names: List[str],  # Names of the attributes to release, in release order
+    device: str = "cuda",         # Device the model is on; gates the CUDA-specific cleanup
+    *,
+    logger: logging.Logger,       # Logger for best-effort failure reporting
+) -> None:
+    """Release one or more model objects: move to CPU, drop references, gc, free CUDA cache.
+
+    For each name in `model_attr_names`, if `obj` has a non-None attribute:
+      1. when on CUDA, best-effort `.to('cpu')` (frees GPU tensors; skipped for
+         objects without a `.to` method, e.g. processors/tokenizers),
+      2. `setattr(obj, name, None)` and drop the local reference.
+    Then a single `gc.collect()` and — on CUDA — `empty_cache()` + `synchronize()`.
+
+    Best-effort throughout: failures are logged and swallowed. Missing or
+    already-None attributes are skipped, so the call is idempotent.
+    """
+    on_cuda = device.startswith("cuda")
+    for name in model_attr_names:
+        val = getattr(obj, name, None)
+        if val is None:
+            continue
+        if on_cuda:
+            try:
+                if hasattr(val, "to"):
+                    val.to("cpu")
+            except Exception as e:
+                logger.warning(f"release_model: .to('cpu') failed for {name!r}: {e}")
+        setattr(obj, name, None)
+        del val
+    gc.collect()
+    if on_cuda and torch.cuda.is_available():
+        try:
+            torch.cuda.empty_cache()
+            torch.cuda.synchronize()
+        except Exception as e:
+            logger.debug(f"release_model: CUDA cleanup failed: {e}")

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils/oom.py

@@ -0,0 +1,54 @@
+"""Convert torch CUDA out-of-memory exceptions into the substrate's typed `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict and reload.
+
+Docs: https://cj-mills.github.io/cjm-torch-plugin-utilsoom.html.md"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/oom.ipynb.
+
+# %% auto #0
+__all__ = ['cuda_oom_to_plugin_resource_error']
+
+# %% ../nbs/oom.ipynb #exports
+import torch
+
+from cjm_plugin_system.core.errors import PluginResourceError, ResourceShortfall
+
+# %% ../nbs/oom.ipynb #cuda-oom
+def cuda_oom_to_plugin_resource_error(
+    exc: BaseException,          # The caught CUDA OOM exception (e.g. torch.cuda.OutOfMemoryError)
+    *,
+    label: str,                  # Context for the message, e.g. "loading model 'X'" or "inference"
+    headroom_mb: float = 100.0,  # Best-effort margin added to `available` to estimate `needed`
+) -> PluginResourceError:        # Typed error for the substrate's CR-7 reactive-retry path
+    """Convert a CUDA out-of-memory exception into a substrate-typed `PluginResourceError`.
+
+    SG-47 Track B: a plugin's GPU inference / model-load site catches
+    `torch.cuda.OutOfMemoryError` and re-raises the result of this helper so the
+    substrate sees a typed resource error (evict + reload + retry via CR-7)
+    instead of an opaque crash.
+
+    `needed` is a best-effort estimate (`available + headroom_mb`): the true
+    required VRAM is unknowable from the exception, and CR-7 triggers eviction
+    regardless of magnitude, so an approximation above `available` is sufficient.
+
+    The caller raises the returned error, preserving the original cause:
+
+        try:
+            model = Model.from_pretrained(repo_id, ...)
+        except torch.cuda.OutOfMemoryError as e:
+            raise cuda_oom_to_plugin_resource_error(e, label=f"loading {repo_id!r}") from e
+    """
+    try:
+        free_bytes = torch.cuda.mem_get_info()[0] if torch.cuda.is_available() else 0
+    except Exception:
+        # mem_get_info can raise on some driver / edge states; fall back to 0.
+        # CR-7 evicts regardless of the reported magnitude, so 0 is safe.
+        free_bytes = 0
+    available_mb = free_bytes / (1024 ** 2)
+    return PluginResourceError(
+        f"CUDA OOM {label}: {exc}",
+        resource_shortfall=ResourceShortfall(
+            resource="gpu_vram_mb",
+            needed=available_mb + headroom_mb,
+            available=available_mb,
+        ),
+    )

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils.egg-info/PKG-INFO

@@ -0,0 +1,165 @@
+Metadata-Version: 2.4
+Name: cjm-torch-plugin-utils
+Version: 0.0.1
+Summary: PyTorch helpers for cjm-plugin-system plugins: GPU memory release, typed CUDA-OOM handling, and device selection.
+Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cj-mills/cjm-torch-plugin-utils
+Project-URL: Documentation, https://cj-mills.github.io/cjm-torch-plugin-utils/
+Keywords: nbdev
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm-plugin-system>=0.0.37
+Requires-Dist: numpy
+Requires-Dist: torch
+Dynamic: license-file
+
+# cjm-torch-plugin-utils
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_torch_plugin_utils
+```
+
+## Project Structure
+
+    nbs/
+    ├── device.ipynb # Resolve a device spec ("auto" / "cpu" / "cuda" / "cuda:N") to a concrete torch device string.
+    ├── memory.ipynb # Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for releasing models, factored out of the per-plugin reimplementations.
+    └── oom.ipynb    # Convert torch CUDA out-of-memory exceptions into the substrate's typed `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict and reload.
+
+Total: 3 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    device["device<br/>Device resolution"]
+    memory["memory<br/>GPU model release"]
+    oom["oom<br/>CUDA OOM handling"]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### Device resolution (`device.ipynb`)
+
+> Resolve a device spec (“auto” / “cpu” / “cuda” / “cuda:N”) to a
+> concrete torch device string.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.device import (
+    resolve_torch_device
+)
+```
+
+#### Functions
+
+``` python
+def resolve_torch_device(
+    spec: str = "auto",  # Requested device: "auto", "cpu", "cuda", or "cuda:N"
+) -> str:                # Concrete device string
+    """
+    Resolve a device spec to a concrete torch device string.
+    
+    `"auto"` resolves to `"cuda"` when CUDA is available, else `"cpu"`. Any
+    explicit spec (`"cpu"`, `"cuda"`, `"cuda:0"`, ...) is returned unchanged.
+    """
+```
+
+### GPU model release (`memory.ipynb`)
+
+> Robust move-to-CPU + drop-references + gc + CUDA-cache cleanup for
+> releasing models, factored out of the per-plugin reimplementations.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.memory import (
+    release_model
+)
+```
+
+#### Functions
+
+``` python
+def release_model(
+    obj: Any,                     # The plugin instance holding the model attribute(s)
+    model_attr_names: List[str],  # Names of the attributes to release, in release order
+    device: str = "cuda",         # Device the model is on; gates the CUDA-specific cleanup
+    *,
+    logger: logging.Logger,       # Logger for best-effort failure reporting
+) -> None
+    """
+    Release one or more model objects: move to CPU, drop references, gc, free CUDA cache.
+    
+    For each name in `model_attr_names`, if `obj` has a non-None attribute:
+      1. when on CUDA, best-effort `.to('cpu')` (frees GPU tensors; skipped for
+         objects without a `.to` method, e.g. processors/tokenizers),
+      2. `setattr(obj, name, None)` and drop the local reference.
+    Then a single `gc.collect()` and — on CUDA — `empty_cache()` + `synchronize()`.
+    
+    Best-effort throughout: failures are logged and swallowed. Missing or
+    already-None attributes are skipped, so the call is idempotent.
+    """
+```
+
+### CUDA OOM handling (`oom.ipynb`)
+
+> Convert torch CUDA out-of-memory exceptions into the substrate’s typed
+> `PluginResourceError` (SG-47 Track B) so CR-7 reactive retry can evict
+> and reload.
+
+#### Import
+
+``` python
+from cjm_torch_plugin_utils.oom import (
+    cuda_oom_to_plugin_resource_error
+)
+```
+
+#### Functions
+
+``` python
+def cuda_oom_to_plugin_resource_error(
+    exc: BaseException,          # The caught CUDA OOM exception (e.g. torch.cuda.OutOfMemoryError)
+    *,
+    label: str,                  # Context for the message, e.g. "loading model 'X'" or "inference"
+    headroom_mb: float = 100.0,  # Best-effort margin added to `available` to estimate `needed`
+) -> PluginResourceError:        # Typed error for the substrate's CR-7 reactive-retry path
+    """
+    Convert a CUDA out-of-memory exception into a substrate-typed `PluginResourceError`.
+    
+    SG-47 Track B: a plugin's GPU inference / model-load site catches
+    `torch.cuda.OutOfMemoryError` and re-raises the result of this helper so the
+    substrate sees a typed resource error (evict + reload + retry via CR-7)
+    instead of an opaque crash.
+    
+    `needed` is a best-effort estimate (`available + headroom_mb`): the true
+    required VRAM is unknowable from the exception, and CR-7 triggers eviction
+    regardless of magnitude, so an approximation above `available` is sufficient.
+    
+    The caller raises the returned error, preserving the original cause:
+    
+        try:
+            model = Model.from_pretrained(repo_id, ...)
+        except torch.cuda.OutOfMemoryError as e:
+            raise cuda_oom_to_plugin_resource_error(e, label=f"loading {repo_id!r}") from e
+    """
+```

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+cjm_torch_plugin_utils/__init__.py
+cjm_torch_plugin_utils/_modidx.py
+cjm_torch_plugin_utils/device.py
+cjm_torch_plugin_utils/memory.py
+cjm_torch_plugin_utils/oom.py
+cjm_torch_plugin_utils.egg-info/PKG-INFO
+cjm_torch_plugin_utils.egg-info/SOURCES.txt
+cjm_torch_plugin_utils.egg-info/dependency_links.txt
+cjm_torch_plugin_utils.egg-info/entry_points.txt
+cjm_torch_plugin_utils.egg-info/requires.txt
+cjm_torch_plugin_utils.egg-info/top_level.txt

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[nbdev]
+cjm_torch_plugin_utils = cjm_torch_plugin_utils._modidx:d

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils.egg-info/requires.txt

@@ -0,0 +1,3 @@
+cjm-plugin-system>=0.0.37
+numpy
+torch

cjm_torch_plugin_utils-0.0.1/cjm_torch_plugin_utils.egg-info/top_level.txt

@@ -0,0 +1 @@
+cjm_torch_plugin_utils

cjm_torch_plugin_utils-0.0.1/pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["setuptools>=64"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cjm-torch-plugin-utils"
+dynamic = ["version"]
+description = "PyTorch helpers for cjm-plugin-system plugins: GPU memory release, typed CUDA-OOM handling, and device selection."
+readme = "README.md"
+requires-python = ">=3.12"
+license = {text = "Apache-2.0"}
+authors = [{name = "Christian J. Mills", email = "9126128+cj-mills@users.noreply.github.com"}]
+keywords = ['nbdev']
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+]
+dependencies = ['cjm-plugin-system>=0.0.37', 'numpy', 'torch']
+
+[project.urls]
+Repository = "https://github.com/cj-mills/cjm-torch-plugin-utils"
+Documentation = "https://cj-mills.github.io/cjm-torch-plugin-utils/"
+
+[project.entry-points.nbdev]
+cjm_torch_plugin_utils = "cjm_torch_plugin_utils._modidx:d"
+
+[tool.setuptools.dynamic]
+version = {attr = "cjm_torch_plugin_utils.__version__"}
+
+[tool.setuptools.packages.find]
+include = ["cjm_torch_plugin_utils"]
+
+[tool.nbdev]

cjm_torch_plugin_utils-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+