verda-inferno 0.4.4__tar.gz

verda_inferno-0.4.4/.gitignore

@@ -0,0 +1,71 @@
+# If you prefer the allow list template instead of the deny list, see community template:
+# https://github.com/github/gitignore/blob/main/community/Golang/Go.AllowList.gitignore
+#
+# Binaries for programs and plugins
+*.exe
+*.exe~
+*.dll
+*.so
+*.dylib
+
+# Test binary, built with `go test -c`
+*.test
+
+# Code coverage profiles and other test artifacts
+*.out
+coverage.*
+*.coverprofile
+profile.cov
+.coverage
+
+# Dependency directories (remove the comment below to include it)
+# vendor/
+
+# Go workspace file
+go.work
+go.work.sum
+
+# env file
+.env
+
+# Editor/IDE
+.idea/
+.vscode/
+
+# Randoms
+target/
+bin/
+
+# Built binaries at repo root
+/inferno
+/inferno-server
+/inferno-nats
+
+.DS_Store
+.AppleDouble
+.LSOverride
+
+test/test_1mb.json
+test/test_10mb.json
+test/test_100mb.json
+test/test_256mb.json
+
+tmp_example_folder
+
+# Python
+venv/
+.venv/
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+*.egg
+.eggs/
+dist/
+.pytest_cache/
+uv.lock
+.mypy_cache/
+*.pyo
+*.pyd
+
+.claude

verda_inferno-0.4.4/LICENSE

@@ -0,0 +1,190 @@
+                                 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 the 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 the 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 any 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
+
+   Copyright 2024-2026 Verda
+
+   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.

verda_inferno-0.4.4/PKG-INFO

@@ -0,0 +1,197 @@
+Metadata-Version: 2.5
+Name: verda-inferno
+Version: 0.4.4
+Summary: Python worker framework for the Verda inference orchestrator
+Project-URL: Homepage, https://github.com/verda-cloud/inferno
+Project-URL: Repository, https://github.com/verda-cloud/inferno
+Project-URL: Documentation, https://github.com/verda-cloud/inferno#readme
+Project-URL: Issues, https://github.com/verda-cloud/inferno/issues
+Author: Verda
+Maintainer-email: Jaakko Varjo <jaakko@verda.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: inference,inferno,ml,orchestrator,unix-socket,verda,worker
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: msgpack>=1.0.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: test
+Requires-Dist: pytest-cov>=5.0; extra == 'test'
+Requires-Dist: pytest-mock>=3.10; extra == 'test'
+Requires-Dist: pytest>=8.0; extra == 'test'
+Description-Content-Type: text/markdown
+
+# Verda Inferno
+
+Python worker framework for [Verda Inferno](https://github.com/verda-cloud/inferno).
+
+## Installation
+
+```bash
+pip install verda-inferno
+```
+
+Or with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv add verda-inferno
+```
+
+## Quick Start
+
+Create a worker with initialization and prediction functions:
+
+```python
+import json
+import inferno
+
+@inferno.initialize
+def setup():
+    """Called once at startup. Load your model here."""
+    global model
+    model = load_my_model()
+
+@inferno.predict
+def predict(payload: bytes) -> inferno.Response:
+    """Called for each inference request."""
+    result = model(payload)
+    return inferno.Response(
+        data=json.dumps(result).encode(),
+        headers={"Content-Type": "application/json"},
+    )
+```
+
+Run it with the Verda server:
+
+```bash
+inferno run server -c config.yaml
+```
+
+Or run the worker directly:
+
+```bash
+python -m inferno main.py --control-socket /tmp/inferno.ctrl.sock --data-socket /tmp/inferno.data.sock --name worker-1
+```
+
+Available flags:
+
+- `--control-socket` — Path to the control Unix socket
+- `--data-socket` — Path to the data Unix socket
+- `--name` — Worker identity name
+- `-c, --config` — Path to a YAML config file (alternative to flags)
+- `--debug` — Enable debug logging
+
+## Ordered Initialization
+
+When your startup sequence requires specific ordering, use `@inferno.initialize` with an order parameter. Functions run in ascending order:
+
+```python
+import inferno
+
+@inferno.initialize(0)
+def load_tokenizer():
+    global tokenizer
+    tokenizer = AutoTokenizer.from_pretrained("model-name")
+
+@inferno.initialize(1)
+def load_model():
+    global model
+    model = AutoModelForCausalLM.from_pretrained("model-name")
+
+@inferno.initialize(2)
+def warm_up():
+    model.generate(tokenizer("warm up", return_tensors="pt").input_ids)
+```
+
+Using `@inferno.initialize` without an argument defaults to order 0. Multiple functions with the same order run in registration order.
+
+## Response Types
+
+The `@inferno.predict` function can return:
+
+- **`inferno.Response`** — includes response data, HTTP headers, and status code (recommended)
+- **`bytes`** — sent as-is with `200 OK` and `application/octet-stream` (backward compatible)
+- **generator yielding `bytes`** — streamed as SSE chunks
+
+```python
+# Return with headers and status code
+@inferno.predict
+def predict(payload: bytes) -> inferno.Response:
+    try:
+        data = json.loads(payload)
+        result = model(data)
+        return inferno.Response(
+            data=json.dumps(result).encode(),
+            headers={"Content-Type": "application/json"},
+        )
+    except ValueError as e:
+        return inferno.Response(
+            data=json.dumps({"error": str(e)}).encode(),
+            headers={"Content-Type": "application/json"},
+            status_code=422,
+        )
+```
+
+## Streaming Responses
+
+Return a generator from your predict function to stream results:
+
+```python
+@inferno.predict
+def predict(payload: bytes):
+    for token in model.generate_stream(payload):
+        yield token.encode()
+```
+
+## Hardware Health
+
+Register a function to report hardware status via the `/hardware-health` endpoint:
+
+```python
+@inferno.hardware_health
+def check_hardware() -> dict:
+    import torch
+    if not torch.cuda.is_available():
+        return {"status": "no cuda device detected"}
+    free, total = torch.cuda.mem_get_info(0)
+    return {
+        "status": "ok",
+        "device": torch.cuda.get_device_properties(0).name,
+        "total_memory_mb": total // (1024 * 1024),
+        "free_memory_mb": free // (1024 * 1024),
+    }
+```
+
+If no `@inferno.hardware_health` function is registered, the endpoint returns `{"status": "not enabled"}`.
+
+## API
+
+- `@inferno.initialize` - Register a startup function (called once, supports ordering)
+- `@inferno.predict` - Register the prediction function (called per request, exactly one required)
+- `@inferno.hardware_health` - Register a hardware health check function (optional)
+- `inferno.Response` - Wrap response data with HTTP headers and status code
+- `inferno.run()` - Start the worker loop programmatically
+
+## How It Works
+
+The inferno package connects to the Verda server via Unix domain sockets using a binary protocol (MessagePack + 12-byte headers). Initialization functions run once at startup in order, and `@inferno.predict` is called for each inference request routed by the server. When a predict function returns `inferno.Response`, the worker sends the data with an `Envelope` data type that carries HTTP headers and status code back to the server.
+
+## Requirements
+
+- Python 3.10+
+- Linux or macOS (Unix domain sockets required)
+
+## License
+
+Apache License 2.0

verda_inferno-0.4.4/README.md

@@ -0,0 +1,163 @@
+# Verda Inferno
+
+Python worker framework for [Verda Inferno](https://github.com/verda-cloud/inferno).
+
+## Installation
+
+```bash
+pip install verda-inferno
+```
+
+Or with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv add verda-inferno
+```
+
+## Quick Start
+
+Create a worker with initialization and prediction functions:
+
+```python
+import json
+import inferno
+
+@inferno.initialize
+def setup():
+    """Called once at startup. Load your model here."""
+    global model
+    model = load_my_model()
+
+@inferno.predict
+def predict(payload: bytes) -> inferno.Response:
+    """Called for each inference request."""
+    result = model(payload)
+    return inferno.Response(
+        data=json.dumps(result).encode(),
+        headers={"Content-Type": "application/json"},
+    )
+```
+
+Run it with the Verda server:
+
+```bash
+inferno run server -c config.yaml
+```
+
+Or run the worker directly:
+
+```bash
+python -m inferno main.py --control-socket /tmp/inferno.ctrl.sock --data-socket /tmp/inferno.data.sock --name worker-1
+```
+
+Available flags:
+
+- `--control-socket` — Path to the control Unix socket
+- `--data-socket` — Path to the data Unix socket
+- `--name` — Worker identity name
+- `-c, --config` — Path to a YAML config file (alternative to flags)
+- `--debug` — Enable debug logging
+
+## Ordered Initialization
+
+When your startup sequence requires specific ordering, use `@inferno.initialize` with an order parameter. Functions run in ascending order:
+
+```python
+import inferno
+
+@inferno.initialize(0)
+def load_tokenizer():
+    global tokenizer
+    tokenizer = AutoTokenizer.from_pretrained("model-name")
+
+@inferno.initialize(1)
+def load_model():
+    global model
+    model = AutoModelForCausalLM.from_pretrained("model-name")
+
+@inferno.initialize(2)
+def warm_up():
+    model.generate(tokenizer("warm up", return_tensors="pt").input_ids)
+```
+
+Using `@inferno.initialize` without an argument defaults to order 0. Multiple functions with the same order run in registration order.
+
+## Response Types
+
+The `@inferno.predict` function can return:
+
+- **`inferno.Response`** — includes response data, HTTP headers, and status code (recommended)
+- **`bytes`** — sent as-is with `200 OK` and `application/octet-stream` (backward compatible)
+- **generator yielding `bytes`** — streamed as SSE chunks
+
+```python
+# Return with headers and status code
+@inferno.predict
+def predict(payload: bytes) -> inferno.Response:
+    try:
+        data = json.loads(payload)
+        result = model(data)
+        return inferno.Response(
+            data=json.dumps(result).encode(),
+            headers={"Content-Type": "application/json"},
+        )
+    except ValueError as e:
+        return inferno.Response(
+            data=json.dumps({"error": str(e)}).encode(),
+            headers={"Content-Type": "application/json"},
+            status_code=422,
+        )
+```
+
+## Streaming Responses
+
+Return a generator from your predict function to stream results:
+
+```python
+@inferno.predict
+def predict(payload: bytes):
+    for token in model.generate_stream(payload):
+        yield token.encode()
+```
+
+## Hardware Health
+
+Register a function to report hardware status via the `/hardware-health` endpoint:
+
+```python
+@inferno.hardware_health
+def check_hardware() -> dict:
+    import torch
+    if not torch.cuda.is_available():
+        return {"status": "no cuda device detected"}
+    free, total = torch.cuda.mem_get_info(0)
+    return {
+        "status": "ok",
+        "device": torch.cuda.get_device_properties(0).name,
+        "total_memory_mb": total // (1024 * 1024),
+        "free_memory_mb": free // (1024 * 1024),
+    }
+```
+
+If no `@inferno.hardware_health` function is registered, the endpoint returns `{"status": "not enabled"}`.
+
+## API
+
+- `@inferno.initialize` - Register a startup function (called once, supports ordering)
+- `@inferno.predict` - Register the prediction function (called per request, exactly one required)
+- `@inferno.hardware_health` - Register a hardware health check function (optional)
+- `inferno.Response` - Wrap response data with HTTP headers and status code
+- `inferno.run()` - Start the worker loop programmatically
+
+## How It Works
+
+The inferno package connects to the Verda server via Unix domain sockets using a binary protocol (MessagePack + 12-byte headers). Initialization functions run once at startup in order, and `@inferno.predict` is called for each inference request routed by the server. When a predict function returns `inferno.Response`, the worker sends the data with an `Envelope` data type that carries HTTP headers and status code back to the server.
+
+## Requirements
+
+- Python 3.10+
+- Linux or macOS (Unix domain sockets required)
+
+## License
+
+Apache License 2.0

verda_inferno-0.4.4/inferno/__init__.py

@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: Apache-2.0
+
+"""
+Verda Inferno - ML Worker Framework
+
+A framework for building ML inference workers that communicate
+with the Verda inference server over Unix sockets.
+
+Usage:
+    import inferno
+
+    @inferno.initialize
+    def setup():
+        # Load model, initialize resources
+        pass
+
+    @inferno.predict
+    def predict(payload: bytes) -> inferno.Response:
+        # Process payload and return result
+        return inferno.Response(data=result, headers={"Content-Type": "application/json"})
+"""
+
+from .decorators import initialize, predict, hardware_health, get_initialize_func, get_predict_func, get_hardware_health_func
+from .response import Response
+from .worker import run
+
+__version__ = "0.4.4"
+__all__ = ["initialize", "predict", "hardware_health", "Response", "run"]