tirx-kernels 0.0.0__tar.gz

tirx_kernels-0.0.0/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.

tirx_kernels-0.0.0/PKG-INFO

@@ -0,0 +1,100 @@
+Metadata-Version: 2.4
+Name: tirx-kernels
+Version: 0.0.0
+Summary: High-performance GPU kernels (GEMM + FlashAttention4) written in TIRx
+Author: MLC AI
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/mlc-ai/tirx-kernels
+Project-URL: Repository, https://github.com/mlc-ai/tirx-kernels
+Project-URL: Issues, https://github.com/mlc-ai/tirx-kernels/issues
+Keywords: tirx,tvm,gpu,kernels,gemm,flash-attention
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# tirx-kernels
+
+High-performance GPU kernels written in [TIRx](https://github.com/apache/tvm).
+
+> **Official PyPI package:** install only from [`tirx-kernels`](https://pypi.org/project/tirx-kernels/)
+> published by this repository ([mlc-ai/tirx-kernels](https://github.com/mlc-ai/tirx-kernels)).
+> Do not use similarly named packages from other publishers.
+
+## Kernels
+
+| Name                 | dtype             | Arch    |
+| -------------------- | ----------------- | ------- |
+| `fp16_bf16_gemm`     | fp16 / bf16       | sm_100a |
+| `fp8_blockwise_gemm` | fp8 (blockwise)   | sm_100a |
+| `nvfp4_gemm`         | nvfp4             | sm_100a |
+| `flash_attention4`   | bf16              | sm_100a |
+
+## Installation
+
+```bash
+pip install tirx-kernels          # from a release
+# or, from a checkout:
+pip install -e .
+```
+
+### External dependencies
+
+These are **not on PyPI** and must be installed/available separately. They are
+imported lazily, so `import tirx_kernels` and kernel discovery work without
+them — they are only needed to actually compile/run a kernel:
+
+| Dependency       | Needed by                          | Notes                                                  |
+| ---------------- | ---------------------------------- | ------------------------------------------------------ |
+| `tvm.tirx`       | all kernels (compile + run)        | The TIRx compiler. Put it on `PYTHONPATH`, e.g. `/path/to/tir/python`. |
+| `torch`          | all kernels                        | CUDA build matching your GPU.                          |
+| `deep_gemm`      | `fp8_blockwise_gemm` data/baseline | Used for fp8 quantization helpers and the reference.   |
+| `flashinfer`     | `nvfp4_gemm` data/baseline         | Used for nvfp4 quantization and the baseline.          |
+
+## Usage
+
+### Command line
+
+```bash
+# List discovered kernels (with their config labels)
+python -m tirx_kernels.registry --format json
+
+# Run correctness tests (optionally filter by kernel / config label)
+python -m tirx_kernels.test
+python -m tirx_kernels.test --kernel fp16_bf16_gemm
+python -m tirx_kernels.test --kernel fp16_bf16_gemm --config bf16_1024x1024x1024
+
+# Benchmark
+python -m tirx_kernels.bench --kernel nvfp4_gemm
+```
+
+### Programmatic API
+
+Every kernel module exposes a small, uniform interface (see
+`tirx_kernels/_protocol.py`):
+
+```python
+from tirx_kernels.registry import discover_kernels
+
+kernels = discover_kernels()          # {name: module}
+mod = kernels["fp16_bf16_gemm"]
+
+mod.run_test(M=1024, N=1024, K=1024)  # compile + run + correctness check
+mod.run_bench(M=1024, N=1024, K=1024) # profile (needs a GPU)
+
+func = mod.get_kernel(M=1024, N=1024, K=1024)  # the TIRx PrimFunc
+```
+
+Each module also provides `KERNEL_META` (name / category / `compute_capability`)
+and `CONFIGS` (the test/bench parameter sweeps) that the registry and CLI use.
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE).

tirx_kernels-0.0.0/README.md

@@ -0,0 +1,78 @@
+# tirx-kernels
+
+High-performance GPU kernels written in [TIRx](https://github.com/apache/tvm).
+
+> **Official PyPI package:** install only from [`tirx-kernels`](https://pypi.org/project/tirx-kernels/)
+> published by this repository ([mlc-ai/tirx-kernels](https://github.com/mlc-ai/tirx-kernels)).
+> Do not use similarly named packages from other publishers.
+
+## Kernels
+
+| Name                 | dtype             | Arch    |
+| -------------------- | ----------------- | ------- |
+| `fp16_bf16_gemm`     | fp16 / bf16       | sm_100a |
+| `fp8_blockwise_gemm` | fp8 (blockwise)   | sm_100a |
+| `nvfp4_gemm`         | nvfp4             | sm_100a |
+| `flash_attention4`   | bf16              | sm_100a |
+
+## Installation
+
+```bash
+pip install tirx-kernels          # from a release
+# or, from a checkout:
+pip install -e .
+```
+
+### External dependencies
+
+These are **not on PyPI** and must be installed/available separately. They are
+imported lazily, so `import tirx_kernels` and kernel discovery work without
+them — they are only needed to actually compile/run a kernel:
+
+| Dependency       | Needed by                          | Notes                                                  |
+| ---------------- | ---------------------------------- | ------------------------------------------------------ |
+| `tvm.tirx`       | all kernels (compile + run)        | The TIRx compiler. Put it on `PYTHONPATH`, e.g. `/path/to/tir/python`. |
+| `torch`          | all kernels                        | CUDA build matching your GPU.                          |
+| `deep_gemm`      | `fp8_blockwise_gemm` data/baseline | Used for fp8 quantization helpers and the reference.   |
+| `flashinfer`     | `nvfp4_gemm` data/baseline         | Used for nvfp4 quantization and the baseline.          |
+
+## Usage
+
+### Command line
+
+```bash
+# List discovered kernels (with their config labels)
+python -m tirx_kernels.registry --format json
+
+# Run correctness tests (optionally filter by kernel / config label)
+python -m tirx_kernels.test
+python -m tirx_kernels.test --kernel fp16_bf16_gemm
+python -m tirx_kernels.test --kernel fp16_bf16_gemm --config bf16_1024x1024x1024
+
+# Benchmark
+python -m tirx_kernels.bench --kernel nvfp4_gemm
+```
+
+### Programmatic API
+
+Every kernel module exposes a small, uniform interface (see
+`tirx_kernels/_protocol.py`):
+
+```python
+from tirx_kernels.registry import discover_kernels
+
+kernels = discover_kernels()          # {name: module}
+mod = kernels["fp16_bf16_gemm"]
+
+mod.run_test(M=1024, N=1024, K=1024)  # compile + run + correctness check
+mod.run_bench(M=1024, N=1024, K=1024) # profile (needs a GPU)
+
+func = mod.get_kernel(M=1024, N=1024, K=1024)  # the TIRx PrimFunc
+```
+
+Each module also provides `KERNEL_META` (name / category / `compute_capability`)
+and `CONFIGS` (the test/bench parameter sweeps) that the registry and CLI use.
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE).

tirx_kernels-0.0.0/pyproject.toml

@@ -0,0 +1,85 @@
+[build-system]
+requires = ["setuptools>=64"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tirx-kernels"
+version = "0.0.0"
+description = "High-performance GPU kernels (GEMM + FlashAttention4) written in TIRx"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.10"
+authors = [{ name = "MLC AI" }]
+keywords = ["tirx", "tvm", "gpu", "kernels", "gemm", "flash-attention"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+# Runtime deps are NOT on PyPI and must be installed separately:
+#   - tvm.tirx (the TIRx compiler)  — required by every kernel
+#   - torch                          — required by every kernel
+#   - deep_gemm                      — optional, fp8_blockwise_gemm reference/baseline
+#   - flashinfer                     — optional, nvfp4_gemm quantization/baseline
+# See README.md "External dependencies". They are imported lazily so
+# `import tirx_kernels` and registry discovery work without them.
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/mlc-ai/tirx-kernels"
+Repository = "https://github.com/mlc-ai/tirx-kernels"
+Issues = "https://github.com/mlc-ai/tirx-kernels/issues"
+
+[tool.setuptools.packages.find]
+include = ["tirx_kernels*"]
+
+[tool.pytest.ini_options]
+# Repo root on sys.path so `import tirx_kernels` resolves without an
+# editable install. TIRx itself (`tvm.tirx`) is user-installed and must
+# stay on the environment (e.g. PYTHONPATH=/home/<user>/tir/python).
+pythonpath = ["."]
+
+[tool.ruff]
+line-length = 100
+indent-width = 4
+target-version = "py310"
+
+[tool.ruff.lint]
+select = [
+  "E",   # pycodestyle errors
+  "F",   # pyflakes
+  "I",   # isort
+  "UP",  # pyupgrade
+  "RUF", # ruff-specific rules
+]
+ignore = [
+  # pyupgrade (style preference or low-value)
+  "UP028", # yield-in-for-loop
+  "UP030", # format-literals
+  "UP031", # printf-string-formatting
+  # ruff (preview rules, not yet stable)
+  "RUF043", # pytest-raises-ambiguous-pattern
+  "RUF059", # unused-unpacked-variable
+]
+fixable = ["ALL"]
+unfixable = []
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["E402", "F401", "F403", "F405"]
+"tirx_kernels/**/*.py" = ["E501", "E741", "F821", "F823", "F841", "F842"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["tvm", "tirx_kernels"]
+split-on-trailing-comma = false
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = true
+line-ending = "auto"
+docstring-code-format = false
+docstring-code-line-length = "dynamic"

tirx_kernels-0.0.0/setup.cfg

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

tirx_kernels-0.0.0/tests/test_registry_overlay.py

@@ -0,0 +1,104 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you 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.
+from __future__ import annotations
+
+import json
+import os
+import subprocess
+import sys
+import textwrap
+from pathlib import Path
+
+_REPO_ROOT = Path(__file__).resolve().parents[1]
+
+
+def _write_kernel(root: Path, category: str, module: str, name: str) -> None:
+    category_dir = root / category
+    category_dir.mkdir(parents=True, exist_ok=True)
+    (category_dir / "__init__.py").write_text("", encoding="utf-8")
+    (category_dir / f"{module}.py").write_text(
+        textwrap.dedent(
+            f"""
+            KERNEL_META = {{
+                "name": "{name}",
+                "category": "{category}",
+                "compute_capability": 100,
+            }}
+            CONFIGS = [{{"label": "tiny"}}]
+            """
+        ),
+        encoding="utf-8",
+    )
+
+
+def _run_with_overlay(overlay_root: Path, code: str) -> subprocess.CompletedProcess[str]:
+    env = os.environ.copy()
+    env["PYTHONPATH"] = str(_REPO_ROOT)
+    env["TIRX_KERNELS_OVERLAY_PATHS"] = str(overlay_root)
+    env.pop("TIRX_KERNELS_EXTRA_CATEGORIES", None)
+    env.pop("TIRX_KERNELS_STRICT", None)
+    return subprocess.run(
+        [sys.executable, "-c", textwrap.dedent(code)],
+        cwd=_REPO_ROOT,
+        env=env,
+        text=True,
+        capture_output=True,
+        check=True,
+    )
+
+
+def test_overlay_can_add_private_category(tmp_path: Path) -> None:
+    overlay_root = tmp_path / "overlay" / "tirx_kernels"
+    _write_kernel(overlay_root, "private", "toy", "private_toy")
+
+    proc = _run_with_overlay(
+        overlay_root,
+        """
+        import json
+        from tirx_kernels.registry import _discover_categories, discover_kernels
+
+        kernels = discover_kernels(category="private")
+        print(json.dumps({
+            "categories": _discover_categories(),
+            "names": sorted(kernels),
+            "category": kernels["private_toy"].KERNEL_META["category"],
+        }))
+        """,
+    )
+
+    data = json.loads(proc.stdout)
+    assert "private" in data["categories"]
+    assert data["names"] == ["private_toy"]
+    assert data["category"] == "private"
+
+
+def test_overlay_can_extend_existing_category(tmp_path: Path) -> None:
+    overlay_root = tmp_path / "overlay" / "tirx_kernels"
+    _write_kernel(overlay_root, "gemm", "overlay_toy", "overlay_gemm_toy")
+
+    proc = _run_with_overlay(
+        overlay_root,
+        """
+        import json
+        from tirx_kernels.registry import discover_kernels
+
+        kernels = discover_kernels(category="gemm")
+        print(json.dumps({"has_overlay": "overlay_gemm_toy" in kernels}))
+        """,
+    )
+
+    assert json.loads(proc.stdout)["has_overlay"]

tirx_kernels-0.0.0/tirx_kernels/__init__.py

@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you 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.
+"""TIRX kernel library.
+
+Private or experimental kernels can be layered on top of the released package by
+setting ``TIRX_KERNELS_OVERLAY_PATHS`` to one or more ``tirx_kernels`` package
+directories, separated by ``os.pathsep``.
+"""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+_OVERLAY_ENV = "TIRX_KERNELS_OVERLAY_PATHS"
+
+
+def _iter_overlay_paths() -> list[Path]:
+    paths = []
+    raw = os.environ.get(_OVERLAY_ENV, "")
+    for item in raw.split(os.pathsep):
+        item = item.strip()
+        if not item:
+            continue
+        path = Path(item).expanduser()
+        if path.is_dir():
+            paths.append(path.resolve())
+    return paths
+
+
+def _append_overlay_paths() -> None:
+    seen = {str(Path(item).resolve()) for item in __path__}
+    for path in _iter_overlay_paths():
+        text = str(path)
+        if text not in seen:
+            __path__.append(text)
+            seen.add(text)
+
+
+_append_overlay_paths()