granite-switch 0.0.1__tar.gz

granite_switch-0.0.1/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

granite_switch-0.0.1/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: granite-switch
+Version: 0.0.1
+Summary: Granite Switch: Embedded LoRA adapter switching for Granite models
+License-Expression: Apache-2.0
+Requires-Python: <3.14,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: transformers>=5.5.1
+Provides-Extra: hf
+Requires-Dist: accelerate>=0.20.0; extra == "hf"
+Provides-Extra: vllm
+Requires-Dist: vllm<0.20.0,>=0.19.1; extra == "vllm"
+Provides-Extra: vllm20
+Requires-Dist: vllm<0.21.0,>=0.20.0; extra == "vllm20"
+Provides-Extra: compose
+Requires-Dist: huggingface_hub; extra == "compose"
+Requires-Dist: pyyaml; extra == "compose"
+Requires-Dist: tqdm; extra == "compose"
+Requires-Dist: safetensors; extra == "compose"
+Provides-Extra: build
+Requires-Dist: huggingface_hub; extra == "build"
+Requires-Dist: pyyaml; extra == "build"
+Requires-Dist: tqdm; extra == "build"
+Requires-Dist: safetensors; extra == "build"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: granite-switch[compose,hf,vllm]; extra == "dev"
+Provides-Extra: dev-vllm20
+Requires-Dist: pytest; extra == "dev-vllm20"
+Requires-Dist: granite-switch[compose,hf,vllm20]; extra == "dev-vllm20"
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Dynamic: license-file
+
+# Granite Switch — Fine-tuning, finally composable
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+
+| [**Browse Adapters**](https://huggingface.co/collections/ibm-granite/granite-libraries) | [Models on HF](https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview) | [Tutorials](tutorials/README.md) |
+
+Task-specific fine-tuning delivers large accuracy gains on small models — but shipping a separate model per task is operationally painful. Granite Switch gives you the accuracy of many models with the footprint of one: compose a single checkpoint from our adapter library in minutes, then swap or upgrade individual capabilities as your needs change.
+
+Browse the full set of ready-to-use adapters in the [Granite Libraries collection](https://huggingface.co/collections/ibm-granite/granite-libraries) on Hugging Face.
+
+## Key Features
+
+- **Composable** — Combine independently trained adapters into one checkpoint, whether IBM's or yours. Swap, upgrade, or customize without retraining.
+- **Fast** — Built on IBM's Activated LoRA technology for efficient KV cache reuse, low latency, and high inference throughput.
+- **Accurate** — Task-specific adapters can match and even surpass the accuracy of significantly larger generalist models, while requiring only a fraction of the serving cost. See the [adapter catalog](https://generative-computing.github.io/granite-switch/adapter_catalog.html#hallucination-detection) for benchmark comparisons across all 12 adapters.
+- **Inference-ready** — Support for Hugging Face and vLLM.
+
+## Quick Start
+
+### Install
+
+```bash
+git clone https://github.com/generative-computing/granite-switch.git
+cd granite-switch
+python -m venv venv && source venv/bin/activate
+
+# Pick what you need:
+pip install -e ".[compose]" # Compose modular models
+pip install -e ".[hf]"      # HuggingFace inference
+pip install -e ".[vllm]"    # vLLM production inference (0.19.x)
+pip install -e ".[vllm20]"  # vLLM 0.20+ (requires CUDA 13+)
+pip install -e ".[dev]"     # Everything (uses vLLM 0.19.x by default)
+pip install -e ".[dev-vllm20]" # Dev environment with vLLM 0.20+
+```
+
+Requires Python 3.9+ and PyTorch 2.0+.
+
+> **vLLM version note:** This project currently defaults to vLLM 0.19.1 due to vLLM 0.20's
+> dependency on CUDA 13.0+ (via PyTorch 2.11), which is incompatible with many existing
+> environments running CUDA 12.x drivers. Use `.[vllm20]` if your environment supports CUDA 13+.
+
+### Compose a Model
+
+Combine a base Granite model with adapters into a single deployable checkpoint:
+
+```bash
+python -m granite_switch.composer.compose_granite_switch \
+  --base-model ibm-granite/granite-4.1-3b \
+  --adapters ibm-granite/granitelib-core-r1.0 ibm-granite/granitelib-rag-r1.0  ibm-granite/granitelib-guardian-r1.0 \
+  --output ./my-model
+```
+
+Use the **[Adapter Composer](https://generative-computing.github.io/granite-switch/adapter_catalog.html)** to browse available adapters, compare benchmarks, and generate a ready-to-run compose command.
+
+This downloads the base model, embeds compatible LoRA adapters (with a preference towards activated LoRA), adds control tokens and a chat template, and produces a model directory that works with both HuggingFace and vLLM.
+
+For convenience, you can find already composed Granite Switch models for the Granite 4.1 model family here:
+
+- [ibm-granite/granite-switch-4.1-3b-preview](https://huggingface.co/ibm-granite/granite-switch-4.1-3b-preview)
+- [ibm-granite/granite-switch-4.1-8b-preview](https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview)
+- [ibm-granite/granite-switch-4.1-30b-preview](https://huggingface.co/ibm-granite/granite-switch-4.1-30b-preview)
+
+
+### Run Inference
+
+**vLLM + Mellea (recommended):**
+
+```bash
+pip install mellea
+python -m vllm.entrypoints.openai.api_server --model ./my-model --port 8000
+```
+
+```python
+from mellea.backends.openai import OpenAIBackend
+from mellea.stdlib.components.intrinsic import rag
+from mellea.stdlib.context import ChatContext
+
+backend = OpenAIBackend(
+    model_id="./my-model",
+    base_url="http://localhost:8000/v1",
+    api_key="unused",
+)
+backend.register_embedded_adapter_model("./my-model")
+
+query = "I want to ask you something. what is...mmmm the the main city(capital you call it,right?) of France?"
+ctx = ChatContext()
+
+rewritten = rag.rewrite_question(query, ctx, backend)
+print(f"original:  {query}")
+print(f"rewritten: {rewritten}")
+# => "What is the capital of France?"
+```
+
+**HuggingFace:**
+
+```python
+import granite_switch.hf  # Register HF backend
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("./my-model", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("./my-model")
+
+messages = [{"role": "user", "content": "What is the capital of France?"}]
+documents = [{"doc_id": "1", "text": "Paris is the capital of France."}]
+
+prompt = tokenizer.apply_chat_template(
+    messages,
+    documents=documents,
+    adapter_name="answerability",  # activates the answerability adapter
+    add_generation_prompt=True,
+    tokenize=False,
+)
+outputs = model.generate(**tokenizer(prompt, return_tensors="pt").to(model.device))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# => "answerable"
+```
+
+## How It Works
+
+Granite Switch uses a **switch layer**—a small attention-based mechanism that reads control tokens from the input and determines which adapter's LoRA weights to apply at each position.
+
+**What makes composition work:**
+
+- **KV cache normalization** — each adapter sees only the base model's KV cache, never another adapter's internal state
+- **No joint training required** — Adapters can be developed, tested, and published independently
+- **Standard inference** — The entire model loads in vLLM with zero code changes
+
+## Documentation
+
+For detailed tutorials and many working examples, see the [Tutorials](tutorials/README.md) section.
+
+## Citation
+
+```bibtex
+@software{granite_switch,
+  title  = {Granite Switch: Coarse-Grained Expert Switching for LLMs},
+  author = {IBM Research},
+  year   = {2025},
+  url    = {https://github.com/ibm-granite/granite-switch}
+}
+```
+
+## IBM ❤️ Open Source AI
+
+Granite Switch was started by IBM Research.
+
+## License
+
+Granite Switch has an Apache-2.0 license, as found in the [LICENSE](LICENSE) file.

granite_switch-0.0.1/README.md

@@ -0,0 +1,151 @@
+# Granite Switch — Fine-tuning, finally composable
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+
+| [**Browse Adapters**](https://huggingface.co/collections/ibm-granite/granite-libraries) | [Models on HF](https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview) | [Tutorials](tutorials/README.md) |
+
+Task-specific fine-tuning delivers large accuracy gains on small models — but shipping a separate model per task is operationally painful. Granite Switch gives you the accuracy of many models with the footprint of one: compose a single checkpoint from our adapter library in minutes, then swap or upgrade individual capabilities as your needs change.
+
+Browse the full set of ready-to-use adapters in the [Granite Libraries collection](https://huggingface.co/collections/ibm-granite/granite-libraries) on Hugging Face.
+
+## Key Features
+
+- **Composable** — Combine independently trained adapters into one checkpoint, whether IBM's or yours. Swap, upgrade, or customize without retraining.
+- **Fast** — Built on IBM's Activated LoRA technology for efficient KV cache reuse, low latency, and high inference throughput.
+- **Accurate** — Task-specific adapters can match and even surpass the accuracy of significantly larger generalist models, while requiring only a fraction of the serving cost. See the [adapter catalog](https://generative-computing.github.io/granite-switch/adapter_catalog.html#hallucination-detection) for benchmark comparisons across all 12 adapters.
+- **Inference-ready** — Support for Hugging Face and vLLM.
+
+## Quick Start
+
+### Install
+
+```bash
+git clone https://github.com/generative-computing/granite-switch.git
+cd granite-switch
+python -m venv venv && source venv/bin/activate
+
+# Pick what you need:
+pip install -e ".[compose]" # Compose modular models
+pip install -e ".[hf]"      # HuggingFace inference
+pip install -e ".[vllm]"    # vLLM production inference (0.19.x)
+pip install -e ".[vllm20]"  # vLLM 0.20+ (requires CUDA 13+)
+pip install -e ".[dev]"     # Everything (uses vLLM 0.19.x by default)
+pip install -e ".[dev-vllm20]" # Dev environment with vLLM 0.20+
+```
+
+Requires Python 3.9+ and PyTorch 2.0+.
+
+> **vLLM version note:** This project currently defaults to vLLM 0.19.1 due to vLLM 0.20's
+> dependency on CUDA 13.0+ (via PyTorch 2.11), which is incompatible with many existing
+> environments running CUDA 12.x drivers. Use `.[vllm20]` if your environment supports CUDA 13+.
+
+### Compose a Model
+
+Combine a base Granite model with adapters into a single deployable checkpoint:
+
+```bash
+python -m granite_switch.composer.compose_granite_switch \
+  --base-model ibm-granite/granite-4.1-3b \
+  --adapters ibm-granite/granitelib-core-r1.0 ibm-granite/granitelib-rag-r1.0  ibm-granite/granitelib-guardian-r1.0 \
+  --output ./my-model
+```
+
+Use the **[Adapter Composer](https://generative-computing.github.io/granite-switch/adapter_catalog.html)** to browse available adapters, compare benchmarks, and generate a ready-to-run compose command.
+
+This downloads the base model, embeds compatible LoRA adapters (with a preference towards activated LoRA), adds control tokens and a chat template, and produces a model directory that works with both HuggingFace and vLLM.
+
+For convenience, you can find already composed Granite Switch models for the Granite 4.1 model family here:
+
+- [ibm-granite/granite-switch-4.1-3b-preview](https://huggingface.co/ibm-granite/granite-switch-4.1-3b-preview)
+- [ibm-granite/granite-switch-4.1-8b-preview](https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview)
+- [ibm-granite/granite-switch-4.1-30b-preview](https://huggingface.co/ibm-granite/granite-switch-4.1-30b-preview)
+
+
+### Run Inference
+
+**vLLM + Mellea (recommended):**
+
+```bash
+pip install mellea
+python -m vllm.entrypoints.openai.api_server --model ./my-model --port 8000
+```
+
+```python
+from mellea.backends.openai import OpenAIBackend
+from mellea.stdlib.components.intrinsic import rag
+from mellea.stdlib.context import ChatContext
+
+backend = OpenAIBackend(
+    model_id="./my-model",
+    base_url="http://localhost:8000/v1",
+    api_key="unused",
+)
+backend.register_embedded_adapter_model("./my-model")
+
+query = "I want to ask you something. what is...mmmm the the main city(capital you call it,right?) of France?"
+ctx = ChatContext()
+
+rewritten = rag.rewrite_question(query, ctx, backend)
+print(f"original:  {query}")
+print(f"rewritten: {rewritten}")
+# => "What is the capital of France?"
+```
+
+**HuggingFace:**
+
+```python
+import granite_switch.hf  # Register HF backend
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("./my-model", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("./my-model")
+
+messages = [{"role": "user", "content": "What is the capital of France?"}]
+documents = [{"doc_id": "1", "text": "Paris is the capital of France."}]
+
+prompt = tokenizer.apply_chat_template(
+    messages,
+    documents=documents,
+    adapter_name="answerability",  # activates the answerability adapter
+    add_generation_prompt=True,
+    tokenize=False,
+)
+outputs = model.generate(**tokenizer(prompt, return_tensors="pt").to(model.device))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# => "answerable"
+```
+
+## How It Works
+
+Granite Switch uses a **switch layer**—a small attention-based mechanism that reads control tokens from the input and determines which adapter's LoRA weights to apply at each position.
+
+**What makes composition work:**
+
+- **KV cache normalization** — each adapter sees only the base model's KV cache, never another adapter's internal state
+- **No joint training required** — Adapters can be developed, tested, and published independently
+- **Standard inference** — The entire model loads in vLLM with zero code changes
+
+## Documentation
+
+For detailed tutorials and many working examples, see the [Tutorials](tutorials/README.md) section.
+
+## Citation
+
+```bibtex
+@software{granite_switch,
+  title  = {Granite Switch: Coarse-Grained Expert Switching for LLMs},
+  author = {IBM Research},
+  year   = {2025},
+  url    = {https://github.com/ibm-granite/granite-switch}
+}
+```
+
+## IBM ❤️ Open Source AI
+
+Granite Switch was started by IBM Research.
+
+## License
+
+Granite Switch has an Apache-2.0 license, as found in the [LICENSE](LICENSE) file.

granite_switch-0.0.1/pyproject.toml

@@ -0,0 +1,62 @@
+[build-system]
+requires = ["setuptools>=64", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "granite-switch"
+version = "0.0.1"
+description = "Granite Switch: Embedded LoRA adapter switching for Granite models"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.10,<3.14"
+dependencies = [
+    "torch>=2.0.0",
+    "transformers>=5.5.1",
+]
+
+[project.optional-dependencies]
+hf = ["accelerate>=0.20.0"]
+vllm = ["vllm>=0.19.1,<0.20.0"]
+vllm20 = ["vllm>=0.20.0,<0.21.0"]
+compose = ["huggingface_hub", "pyyaml", "tqdm", "safetensors"]
+build = ["huggingface_hub", "pyyaml", "tqdm", "safetensors"]  # Backward compatibility alias for compose
+dev = ["pytest", "granite-switch[hf,vllm,compose]"]
+dev-vllm20 = ["pytest", "granite-switch[hf,vllm20,compose]"]
+test = ["pytest"]
+
+[project.entry-points."vllm.general_plugins"]
+register_granite_switch = "granite_switch.vllm:register"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = ["--ignore=tests/_legacy", "-m", "not deep"]
+markers = [
+    "gpu: requires CUDA GPU",
+    "vllm: requires vLLM installed",
+    "slow: takes > 30s",
+    "deep: expensive code-theory tests (m=8 / 256-dim); run with: pytest -m deep",
+    "requires_model: needs a real model checkpoint",
+]
+
+[tool.uv]
+conflicts = [
+    [
+        { extra = "vllm" },
+        { extra = "vllm20" },
+    ],
+    [
+        { extra = "dev" },
+        { extra = "vllm20" },
+    ],
+    [
+        { extra = "dev" },
+        { extra = "dev-vllm20" },
+    ],
+    [
+        { extra = "dev-vllm20" },
+        { extra = "vllm" },
+    ],
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]

granite_switch-0.0.1/setup.cfg

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

granite_switch-0.0.1/src/granite_switch/__init__.py

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: Apache-2.0
+"""Granite Switch: Embedded LoRA adapter switching for Granite models."""
+
+__version__ = "0.1.0"
+
+from .config import GraniteSwitchConfig
+
+__all__ = ["GraniteSwitchConfig", "__version__"]

granite_switch-0.0.1/src/granite_switch/composer/__init__.py

@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: Apache-2.0
+"""Compose utilities for Granite Switch models.
+
+This module provides utilities for composing Granite Switch checkpoints from
+base models and LoRA adapters.
+"""
+
+from .weight_remapper import AdapterRemapper, RemapResult
+from .compose_utils import GraniteSwitchComposer
+from .arch import (
+    ArchDescriptor,
+    ModuleDescriptor,
+    resolve_arch,
+    granite_dense_arch,
+    granite_moe_hybrid_arch,
+)
+
+__all__ = [
+    "AdapterRemapper",
+    "RemapResult",
+    "GraniteSwitchComposer",
+    "ArchDescriptor",
+    "ModuleDescriptor",
+    "resolve_arch",
+    "granite_dense_arch",
+    "granite_moe_hybrid_arch",
+]