Set version to 0.6.1

.github/workflows/build_documentation.yaml

@@ -1,17 +0,0 @@
-name: Build documentation
-
-on:
-  push:
-    branches:
-      - main
-      - doc-builder*
-      - v*-release
-
-jobs:
-  build:
-    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@main
-    with:
-      commit_sha: ${{ github.sha }}
-      package: kernels
-    secrets:
-      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}

.github/workflows/build_pr_documentation.yaml

@@ -1,15 +0,0 @@
-name: Build PR Documentation
-
-on: pull_request
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
-    with:
-      commit_sha: ${{ github.event.pull_request.head.sha }}
-      pr_number: ${{ github.event.number }}
-      package: kernels

.github/workflows/lint.yml

@@ -8,24 +8,3 @@ jobs:
       - uses: actions/checkout@v4
       - name: Run ruff
         uses: astral-sh/ruff-action@v3
-
-  black:
-    name: Run black check
-    runs-on: ubuntu-latest
-    env:
-      UV_PYTHON_PREFERENCE: only-managed
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install uv and set the python version
-        uses: astral-sh/setup-uv@v5
-        with:
-          python-version: 3.12
-
-      - name: Install black
-        run: uv pip install black
-
-      - name: Check formatting
-        run: |
-          uv run black --check src
-          uv run black --check tests

.github/workflows/test.yml

@@ -51,10 +51,7 @@ jobs:
         run: uv run mypy src/kernels
 
       - name: Run tests
-        env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        run: |
-          uv run pytest tests
+        run: uv run pytest tests
 
       - name: Check kernel conversion
         run: |
@@ -66,7 +63,7 @@ jobs:
       - name: Check README generation
         # For now, just checks that generation doesn't fail.
         run: |
-          uv run kernels generate-readme kernels-community/triton-layer-norm
+          uv run kernels generate-readme kernels-community/triton-layer-norm --revision docs
 
       - name: Import check without torch
         run: |

.github/workflows/upload_pr_documentation.yaml

@@ -1,16 +0,0 @@
-name: Upload PR Documentation
-
-on:
-  workflow_run:
-    workflows: ["Build PR Documentation"]
-    types:
-      - completed
-
-jobs:
-  build:
-    uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
-    with:
-      package_name: kernels
-    secrets:
-      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
-      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}

README.md

@@ -56,12 +56,10 @@ the Hub.
 
 ## 📚 Documentation
 
-- [Introduction](docs/source/index.md)
-- [Installation](docs/source/installation.md)
-- [Basic usage](docs/source/basic-usage.md)
-- [Using layers](docs/source/layers.md)
-- [Locking kernel/layer versions](docs/source/locking.md)
-- [Environment variables](docs/source/env.md)
-- [Kernel requirements](docs/source/kernel-requirements.md)
-- [Frequently Asked Questions](docs/source/faq.md)
+- [Using layers](docs/layers.md)
+- [Locking kernel versions](docs/locking.md)
+- [Environment variables](docs/env.md)
+- [Using kernels in a Docker container](docs/docker.md)
+- [Kernel requirements](docs/kernel-requirements.md)
+- [Frequently Asked Questions](docs/faq.md)
 - [Writing kernels](https://github.com/huggingface/kernel-builder/blob/main/docs/writing-kernels.md) using [kernel-builder](https://github.com/huggingface/kernel-builder/)

docs/docker.md

@@ -0,0 +1,8 @@
+# Using kernels in a Docker container
+
+build and run the reference [examples/basic.py](examples/basic.py) in a Docker container with the following commands:
+
+```bash
+docker build --platform linux/amd64 -t kernels-reference -f docker/Dockerfile.reference .
+docker run --gpus all -it --rm -e HF_TOKEN=$HF_TOKEN kernels-reference
+```

docs/faq.md

@@ -0,0 +1,13 @@
+# FAQ
+
+## Why is the kernelization step needed?
+
+In earlier versions of `kernels`, a layer's `forward` was replaced by
+`use_kernel_forward_from_hub` and `replace_kernel_forward_from_hub`. The
+new `forward` would dispatch to a kernel based on the device type,
+whether a model was training, etc. However, this approach was
+fundamentally incompatible with `torch.compile` since it relied
+on data-dependent branching.
+
+To avoid branching, we have to make dispatch decisions ahead of time,
+which is what the `kernelize` function does.

docs/kernel-requirements.md

@@ -34,8 +34,6 @@ Kernels are versioned on the Hub using Git tags. Version tags must be of
 the form `v<major>.<minor>.<patch>`. Versions are used by [locking](./locking.md)
 to resolve the version constraints.
 
-We recommend using [semver](https://semver.org/) to version kernels.
-
 ## Native Python module
 
 Kernels will typically contain a native Python module with precompiled
@@ -52,12 +50,13 @@ have dynamic library dependencies outside:
   for compatibility with Python 3.9 and later.
 - Compatible with [`manylinux_2_28`](https://github.com/pypa/manylinux?tab=readme-ov-file#manylinux_2_28-almalinux-8-based).
   This means that the extension **must not** use symbols versions higher than:
+
   - GLIBC 2.28
   - GLIBCXX 3.4.24
   - CXXABI 1.3.11
   - GCC 7.0.0
 
-These requirements can be checked with the ABI checker (see below).
+These requirement can be checked with the ABI checker (see below).
 
 ### macOS
 

docs/layers.md

@@ -0,0 +1,134 @@
+# Layers
+
+A kernel can provide layers in addition to kernel functions. A layer from
+the Hub can replace the `forward` method of an existing layer for a certain
+device type. This makes it possible to provide more performant kernels for
+existing layers.
+
+See [Kernel requirements](kernel-requirements.md) for more information the
+requirements of Hub layers.
+
+## Making a layer extensible with kernels from the hub
+
+### Using a decorator
+
+A layer can be made extensible with the `use_kernel_forward_from_hub`
+decorator. For example:
+
+```python
+@use_kernel_forward_from_hub("SiluAndMul")
+class SiluAndMul(nn.Module):
+    def forward(self, input: torch.Tensor) -> torch.Tensor:
+        d = input.shape[-1] // 2
+        return F.silu(input[..., :d]) * input[..., d:]
+```
+
+The decorator does not change the behavior of the class -- it annotates
+the class with the given name (here `SiluAndMul`). The `kernelize` function
+described below uses this name to look up kernels for the layer.
+
+### External layers
+
+An existing layer that does not (yet) have the `use_kernel_forward_from_hub`
+decorator can be made extensible using the `replace_kernel_forward_from_hub`
+function:
+
+```python
+from somelibrary import SiluAndMul
+
+replace_kernel_forward_from_hub(SiluAndMul, "SiluAndMul")
+```
+
+**Warning:** we strongly recommend using layers with a decorator, since
+it signifies that the maintainer intends to keep the `forward` signature
+compatible with layers from the hub.
+
+## Kernelizing a model
+
+A model will not use Hub kernels by default, even if it contains extensible
+layers. To enable the use of Hub kernels in the model, it needs to be
+'kernelized' using the `kernelize` function. This function traverses the
+model graph and replaces the `forward` methods of extensible layers for which
+Hub kernels are registered. Kernelize can be used as follows:
+
+```python
+model = MyModel(...)
+model = kernelize(model)
+```
+
+**Note:** the `kernelize` function modifies the model in-place, the model
+itself is returned as a convenience.
+
+### Kernel device
+
+Kernels can be registered per device type. For instance, separate `cuda` and
+`metal` kernels could be registered for the name `SiluAndMul`. By default,
+`kernelize` will try to infer the device type from the model's parameters.
+You can pass the device type to `kernelize` if the device type cannot be
+inferred (e.g. because the model has no parameters):
+
+```python
+model = MyModel(...)
+model = kernelize(model, device="cuda")
+```
+
+### `torch.compile`
+
+Not all Hub kernels support `torch.compile`. If you want to compile a model
+after kernelizing it, pass the `needs_torch_compile` argument to ensure that
+only kernels that support `torch.compile` will be loaded:
+
+```python
+model = MyModel(...)
+model = kernelize(model, needs_torch_compile=True)
+```
+
+### Fallback forward
+
+The `needs_torch_compile` argument will fall back to the layer's original
+`forward` if the registered kernels does not support `torch.compile`. You
+can let `kernelize` raise an exception instead by using `use_fallback=False`:
+
+```python
+model = MyModel(...)
+model = kernelize(model, needs_torch_compile=True, use_fallback=False)
+```
+
+This can be useful if you want to guarantee that Hub kernels are used.
+
+## Registering a hub kernel for a layer
+
+`kernelize`` relies on kernel mappings to find Hub kernels for layers.
+Kernel mappings map a kernel name such as `SiluAndMul` to a kernel on
+the Hub. For example:
+
+```python
+kernel_layer_mapping = {
+    "SiluAndMul": {
+        "cuda": LayerRepository(
+            repo_id="kernels-community/activation",
+            layer_name="SiluAndMul",
+            revision="layers",
+        )
+    }
+}
+```
+
+You can register such a mapping using `register_kernel_mapping`:
+
+```python
+register_kernel_mapping(kernel_layer_mapping)
+```
+
+This will register the kernel mapping in the current context, which is
+normally global. It is recommended to scope the mapping to where it is
+used with the `use_kernel_mapping` context manager:
+
+```python
+with use_kernel_mapping(kernel_layer_mapping):
+    # Use the layer for which the mapping is applied.
+    model = kernelize(model)
+```
+
+This ensures that the mapping is not active anymore outside the
+`with`-scope.

docs/locking.md

@@ -1,4 +1,4 @@
-# Locking kernel/layer versions
+# Locking kernel versions
 
 Projects that use `setuptools` can lock the kernel versions that should be
 used. First specify the accepted versions in `pyproject.toml` and make
@@ -26,24 +26,6 @@ activation = get_locked_kernel("kernels-community/activation")
 **Note:** the lock file is included in the package metadata, so it will only be visible
 to `kernels` after doing an (editable or regular) installation of your project.
 
-## Locked kernel layers
-
-Locking is also supported for kernel layers. To use locked layers, register them
-with the `LockedLayerRepository` class:
-
-```python
-kernel_layer_mapping = {
-    "SiluAndMul": {
-        "cuda": LockedLayerRepository(
-            repo_id="kernels-community/activation",
-            layer_name="SiluAndMul",
-        )
-    }
-}
-
-register_kernel_mapping(kernel_layer_mapping)
-```
-
 ## Pre-downloading locked kernels
 
 Locked kernels can be pre-downloaded by running `kernels download .` in your

docs/source/_toctree.yml

@@ -1,30 +0,0 @@
-- sections:
-    - local: index
-      title: Introduction
-    - local: installation
-      title: Installation
-  title: Getting started
-- sections:
-    - local: basic-usage
-      title: Basic Usage
-    - local: layers
-      title: Using Layers
-    - local: locking
-      title: Locking Kernel Versions
-    - local: env
-      title: Environment Variables
-    - local: faq
-      title: FAQ
-  title: Usage Guide
-- sections:
-    - local: api/kernels
-      title: Kernels
-    - local: api/layers
-      title: Layers
-    - local: cli
-      title: Kernels CLI
-  title: API Reference
-- sections:
-    - local: kernel-requirements
-      title: Kernel Requirements
-  title: Developer Guide

docs/source/api/kernels.md

@@ -1,21 +0,0 @@
-# Kernels API Reference
-
-## Main Functions
-
-### get_kernel
-
-[[autodoc]] kernels.get_kernel
-
-### has_kernel
-
-[[autodoc]] kernels.has_kernel
-
-## Loading locked kernels
-
-### load_kernel
-
-[[autodoc]] kernels.load_kernel
-
-### get_locked_kernel
-
-[[autodoc]] kernels.get_locked_kernel

docs/source/api/layers.md

@@ -1,41 +0,0 @@
-# Layers API Reference
-
-## Making layers kernel-aware
-
-### use_kernel_forward_from_hub
-
-[[autodoc]] kernels.use_kernel_forward_from_hub
-
-### replace_kernel_forward_from_hub
-
-[[autodoc]] kernels.replace_kernel_forward_from_hub
-
-## Registering kernel mappings
-
-### use_kernel_mapping
-
-[[autodoc]] kernels.use_kernel_mapping
-
-### register_kernel_mapping
-
-[[autodoc]] kernels.register_kernel_mapping
-
-## Kernelizing a model
-
-### kernelize
-
-[[autodoc]] kernels.kernelize
-
-## Classes
-
-### Device
-
-[[autodoc]] kernels.Device
-
-### Mode
-
-[[autodoc]] kernels.Mode
-
-### LayerRepository
-
-[[autodoc]] kernels.LayerRepository

docs/source/basic-usage.md

@@ -1,50 +0,0 @@
-# Basic Usage
-
-## Loading Kernels
-
-Here is how you would use the [activation](https://huggingface.co/kernels-community/activation) kernels from the Hugging Face Hub:
-
-```python
-import torch
-from kernels import get_kernel
-
-# Download optimized kernels from the Hugging Face hub
-activation = get_kernel("kernels-community/activation")
-
-# Create a random tensor
-x = torch.randn((10, 10), dtype=torch.float16, device="cuda")
-
-# Run the kernel
-y = torch.empty_like(x)
-activation.gelu_fast(y, x)
-
-print(y)
-```
-
-### Using version bounds
-
-Kernels are versioned using tags of the form `v<major>.<minor>.<patch>`.
-You can specify which version to download using Python version specifiers:
-
-```python
-import torch
-from kernels import get_kernel
-
-activation = get_kernel("kernels-community/activation", version=">=0.0.4,<0.1.0")
-```
-
-This will get the latest kernel tagged `v0.0.z` where `z` is at least 4. It
-is strongly recommended to specify a version bound, since a kernel author
-might push incompatible changes to the `main` branch.
-
-## Checking Kernel Availability
-
-You can check if a specific kernel is available for your environment:
-
-```python
-from kernels import has_kernel
-
-# Check if kernel is available for current environment
-is_available = has_kernel("kernels-community/activation")
-print(f"Kernel available: {is_available}")
-```

docs/source/cli.md

@@ -1,41 +0,0 @@
-# Kernels CLI Reference
-
-## Main Functions
-
-### kernels to-wheel
-
-We strongly recommend downloading kernels from the Hub using the `kernels`
-package, since this comes with large [benefits](index.md) over using Python
-wheels. That said, some projects may require deployment of kernels as
-wheels. The `kernels` utility provides a simple solution to this. You can
-convert any Hub kernel into a set of wheels with the `to-wheel` command:
-
-```bash
-$ kernels to-wheel drbh/img2grey 1.1.2
-☸ img2grey-1.1.2+torch27cu128cxx11-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch26cu124cxx11-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch26cu126cxx11-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch27cu126cxx11-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch26cu126cxx98-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch27cu128cxx11-cp39-abi3-manylinux_2_28_aarch64.whl
-☸ img2grey-1.1.2+torch26cu126cxx98-cp39-abi3-manylinux_2_28_aarch64.whl
-☸ img2grey-1.1.2+torch27cu126cxx11-cp39-abi3-manylinux_2_28_aarch64.whl
-☸ img2grey-1.1.2+torch26cu126cxx11-cp39-abi3-manylinux_2_28_aarch64.whl
-☸ img2grey-1.1.2+torch26cu118cxx98-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch26cu124cxx98-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch26cu118cxx11-cp39-abi3-manylinux_2_28_x86_64.whl
-☸ img2grey-1.1.2+torch27cu118cxx11-cp39-abi3-manylinux_2_28_x86_64.whl
-```
-
-### kernels upload
-
-Use `kernels upload <dir_containing_build> --repo_id="hub-username/kernel"` to upload
-your kernel builds to the Hub.
-
-**Notes**:
-
-- This will take care of creating a repository on the Hub with the `repo_id` provided.
-- If a repo with the `repo_id` already exists and if it contains a `build` with the build variant
-  being uploaded, it will attempt to delete the files existing under it.
-- Make sure to be authenticated (run `hf auth login` if not) to be able to perform uploads to the Hub.
-

docs/source/faq.md

@@ -1,41 +0,0 @@
-# FAQ
-
-## Kernel layers
-
-### Why is the kernelization step needed as a separate step?
-
-In earlier versions of `kernels`, a layer's `forward` method was replaced
-by `use_kernel_forward_from_hub` and `replace_kernel_forward_from_hub`.
-The new `forward` would dispatch to a kernel based on the device type,
-whether a model was training, etc. However, this approach was
-fundamentally incompatible with `torch.compile` since it relied
-on data-dependent branching.
-
-To avoid branching, we have to make dispatch decisions ahead of time,
-which is what the `kernelize` function does.
-
-### Why does kernelization only replace `forward` methods?
-
-There are some other possible approaches. The first is to completely
-replace existing layers by kernel layers. However, since this would
-permit free-form layer classes, it would be much harder to validate
-that layers are fully compatible with the layers that they are
-replacing. For instance, they could have completely different member
-variables. Besides that, we would also need to hold on to the original
-layers, in case we need to revert to the base layers when the model
-is `kernelize`d again with different options.
-
-A second approach would be to make an auxiliary layer that wraps the
-original layer and the kernel layer and dispatches to the kernel layer.
-This wouldn't have the issues of the first approach, because kernel layers
-could be similarly strict as they are now, and we would still have access
-to the original layers when `kernelize`-ing the model again. However,
-this would change the graph structure of the model and would break use
-cases where programs access the model internals (e.g.
-`model.layers[0].attention.query_weight`) or rely on the graph structure
-in other ways.
-
-The approach of `forward`-replacement is the least invasive, because
-it preserves the original model graph. It is also reversible, since
-even though the `forward` of a layer _instance_ might be replaced,
-the corresponding class still has the original `forward`.

docs/source/index.md

@@ -1,20 +0,0 @@
-# Kernels
-
-<div align="center">
-<img src="https://github.com/user-attachments/assets/64a652f3-0cd3-4829-b3c1-df13f7933569" width="450" height="450" alt="kernel-builder logo">
-</div>
-
-The Kernel Hub allows Python libraries and applications to load compute
-kernels directly from the [Hub](https://hf.co/). To support this kind
-of dynamic loading, Hub kernels differ from traditional Python kernel
-packages in that they are made to be:
-
-- **Portable**: a kernel can be loaded from paths outside `PYTHONPATH`.
-- **Unique**: multiple versions of the same kernel can be loaded in the
-  same Python process.
-- **Compatible**: kernels must support all recent versions of Python and
-  the different PyTorch build configurations (various CUDA versions
-  and C++ ABIs). Furthermore, older C library versions must be supported.
-
-You can [search for kernels](https://huggingface.co/models?other=kernel) on
-the Hub.

docs/source/installation.md

@@ -1,16 +0,0 @@
-# Installation
-
-Install the `kernels` package with `pip` (requires `torch>=2.5` and CUDA):
-
-```bash
-pip install kernels
-```
-
-# Using kernels in a Docker container
-
-Build and run the reference `examples/basic.py` in a Docker container with the following commands:
-
-```bash
-docker build --platform linux/amd64 -t kernels-reference -f docker/Dockerfile.reference .
-docker run --gpus all -it --rm -e HF_TOKEN=$HF_TOKEN kernels-reference
-```

docs/source/layers.md

@@ -1,323 +0,0 @@
-# Layers
-
-A kernel can provide layers in addition to kernel functions. A layer from
-the Hub can replace the `forward` method of an existing layer for a certain
-device type. This makes it possible to provide more performant kernels for
-existing layers.
-
-See [Kernel requirements](kernel-requirements.md) for more information on the
-requirements of Hub layers.
-
-## Making a layer extensible with kernels from the hub
-
-### Using a decorator
-
-A layer can be made extensible with the `use_kernel_forward_from_hub`
-decorator. For example:
-
-```python
-@use_kernel_forward_from_hub("SiluAndMul")
-class SiluAndMul(nn.Module):
-    def forward(self, input: torch.Tensor) -> torch.Tensor:
-        d = input.shape[-1] // 2
-        return F.silu(input[..., :d]) * input[..., d:]
-```
-
-The decorator does not change the behavior of the class -- it annotates
-the class with the given name (here `SiluAndMul`). The `kernelize` function
-described below uses this name to look up kernels for the layer.
-
-### External layers
-
-An existing layer that does not (yet) have the `use_kernel_forward_from_hub`
-decorator can be made extensible using the `replace_kernel_forward_from_hub`
-function:
-
-```python
-from somelibrary import SiluAndMul
-
-replace_kernel_forward_from_hub(SiluAndMul, "SiluAndMul")
-```
-
-**Warning:** we strongly recommend using layers with a decorator, since
-it signifies that the maintainer intends to keep the `forward` signature
-compatible with layers from the hub.
-
-## Kernelizing a model
-
-A model will not use Hub kernels by default, even if it contains extensible
-layers. To enable the use of Hub kernels in the model, it needs to be
-'kernelized' using the `kernelize` function. This function traverses the
-model graph and replaces the `forward` methods of extensible layers for which
-Hub kernels are registered. `kernelize` can be used as follows:
-
-```python
-model = MyModel(...)
-model = kernelize(model, mode=Mode.INFERENCE)
-```
-
-The `kernelize` function modifies the model in-place, the model itself is
-returned as a convenience. The `mode` specifies that the model will be used
-in inference. Similarly, you can ask `kernelize` to prepare the model for
-training:
-
-```python
-model = MyModel(...)
-model = kernelize(model, mode=Mode.TRAINING)
-```
-
-A model that is kernelized for training can also be used for inference, but
-not the other way around. If you want to change the mode of the kernelized
-model, you can just run `kernelize` on the model again with the new mode.
-
-If you want to compile a model with `torch.compile`, this should be indicated
-in the mode as well. You can do this by combining `Mode.INFERENCE` or
-`Mode.TRAINING` with `Mode.TORCH_COMPILE` using the set union (`|`) operator:
-
-```python
-model = MyModel(...)
-
-# Inference
-model = kernelize(model, mode=Mode.INFERENCE | Mode.TORCH_COMPILE)
-
-# Training
-model = kernelize(model, mode=Mode.TRAINING | Mode.TORCH_COMPILE)
-```
-
-### Kernel device
-
-Kernels can be registered per device type. For instance, separate `cuda` and
-`metal` kernels could be registered for the name `SiluAndMul`. By default,
-`kernelize` will try to infer the device type from the model's parameters.
-You can pass the device type to `kernelize` if the device type cannot be
-inferred (e.g. because the model has no parameters):
-
-```python
-model = MyModel(...)
-model = kernelize(model, device="cuda", mode=Mode.INFERENCE)
-```
-
-### Fallback `forward`
-
-If the `TRAINING` and/or `TORCH_COMPILE` modes are used, but a registered
-kernel does not support backward passes or `torch.compile` respectively,
-`kernelize` will fall back to the original, non-kernelized, layer. You
-can let `kernelize` raise an exception instead by using `use_fallback=False`:
-
-```python
-model = MyModel(...)
-model = kernelize(model, mode=Mode.INFERENCE | Mode.TORCH_COMPILE, use_fallback=False)
-```
-
-This can be useful if you want to guarantee that Hub kernels are used.
-
-### Inspecting which kernels are used
-
-The kernels that are used are logged at the `INFO` level by `kernelize`.
-See the [Python logging](https://docs.python.org/3/library/logging.html)
-documentation for information on how to configure logging.
-
-## Registering a hub kernel for a layer
-
-`kernelize` relies on kernel mappings to find Hub kernels for layers.
-Kernel mappings map a kernel name such as `SiluAndMul` to a kernel on
-the Hub. For example:
-
-```python
-kernel_layer_mapping = {
-    "SiluAndMul": {
-        "cuda": LayerRepository(
-            repo_id="kernels-community/activation",
-            layer_name="SiluAndMul",
-        ),
-        "rocm": LayerRepository(
-            repo_id="kernels-community/activation",
-            layer_name="SiluAndMul",
-        )
-    }
-}
-```
-
-You can register such a mapping using `register_kernel_mapping`:
-
-```python
-register_kernel_mapping(kernel_layer_mapping)
-```
-
-This will register the kernel mapping in the current context, which is
-normally global. It is recommended to scope the mapping to where it is
-used with the `use_kernel_mapping` context manager:
-
-```python
-with use_kernel_mapping(kernel_layer_mapping):
-    # Use the layer for which the mapping is applied.
-    model = kernelize(model, mode=Mode.TRAINING | Mode.TORCH_COMPILE)
-```
-
-This ensures that the mapping is not active anymore outside the
-`with`-scope.
-
-### Using version bounds
-
-Kernels are versioned using tags of the form `v<major>.<minor>.<patch>`.
-You can specify which version of the kernel to download using Python version
-specifiers:
-
-```python
-kernel_layer_mapping = {
-    "SiluAndMul": {
-        "cuda": LayerRepository(
-            repo_id="kernels-community/activation",
-            layer_name="SiluAndMul",
-            version=">=0.0.4,<0.1.0",
-        ),
-        "rocm": LayerRepository(
-            repo_id="kernels-community/activation",
-            layer_name="SiluAndMul",
-            version=">=0.0.4,<0.1.0",
-        )
-    }
-}
-```
-
-This will get the layer from latest kernel tagged `v0.0.z` where `z` is at
-least 4. It is strongly recommended to specify a version bound, since a
-kernel author might push incompatible changes to the `main` branch.
-
-### Registering kernels for specific modes
-
-You might want to register two different kernels for a particular layer,
-where one kernel is optimized for a specific mode. You can do so by
-registering layer repositories for specific modes. For example:
-
-```python
-kernel_layer_mapping = {
-    "SiluAndMul": {
-        "cuda": {
-          Mode.INFERENCE: LayerRepository(
-              repo_id="kernels-community/activation-inference-optimized",
-              layer_name="SiluAndMul",
-          ),
-          Mode.TRAINING | Mode.TORCH_COMPILE: LayerRepository(
-              repo_id="kernels-community/activation-training-optimized",
-              layer_name="SiluAndMul",
-          ),
-      }
-    }
-}
-```
-
-The `kernelize` function will attempt to use the following registered
-kernels for a given mode:
-
-- `INFERENCE`: `INFERENCE` → `INFERENCE | TORCH_COMPILE` → `TRAINING` →
-  `TRAINING | TORCH_COMPILE` → `FALLBACK`
-- `INFERENCE | TORCH_COMPILE`: `INFERENCE | TORCH_COMPILE` →
-  `TRAINING | TORCH_COMPILE` → `FALLBACK`
-- `TRAINING`: `TRAINING` → `TRAINING | TORCH_COMPILE` → `FALLBACK`
-- `TRAINING | TORCH_COMPILE`: `TRAINING | TORCH_COMPILE` → `FALLBACK`
-
-`Mode.FALLBACK` is a special mode that is used when no other mode matches. It
-is also used when a kernel is registered without a mode, as described in the
-previous section.
-
-```python
-kernel_layer_mapping = {
-    "SiluAndMul": {
-        "cuda": {
-            Mode.FALLBACK: LayerRepository(
-                repo_id="kernels-community/activation",
-                layer_name="SiluAndMul",
-            ),
-            Mode.INFERENCE: LayerRepository(
-                repo_id="kernels-community/activation-inference-optimized",
-                layer_name="SiluAndMul",
-            ),
-            Mode.TRAINING: LayerRepository(
-                repo_id="kernels-community/activation-training-optimized",
-                layer_name="SiluAndMul",
-            ),
-        }
-    }
-}
-```
-
-In this case, both `Mode.INFERENCE | Mode.TORCH_COMPILE` and
-`Mode.TRAINING | Mode.TORCH_COMPILE` will use the `Mode.FALLBACK` kernel,
-since the other kernels do not support `torch.compile`.
-
-### Registering kernels for specific CUDA capabilities
-
-Some kernels only work with newer CUDA architectures. For instance, some
-kernels require capability 9.0 for the TMA unit on Hopper GPUs. `kernels`
-supports registering layers for a range of CUDA capabilities. To do so,
-you need to register the layer for a `Device` with type `cuda` and
-set the supported range of CUDA capabilities with using `CUDAProperties`:
-
-```python
-kernel_layer_mapping = {
-    "SiluAndMul": {
-        Device(
-            type="cuda",
-            properties=CUDAProperties(
-                min_capability=75, max_capability=89
-            ),
-        ): LayerRepository(
-            repo_id="kernels-community/activation",
-            layer_name="SiluAndMul",
-        ),
-        Device(
-            type="cuda",
-            properties=CUDAProperties(
-                min_capability=90, max_capability=sys.maxsize
-            ),
-        ): LayerRepository(
-            repo_id="kernels-community/activation-hopper",
-            layer_name="SiluAndMul",
-        ),
-    }
-}
-```
-
-Capabilities behave as follows:
-
-- The minimum and maximum capabilities are inclusive.
-- When a new kernel is registered with the same min/max capabilities as
-  an existing kernel, the new kernel will replace the old kernel.
-- When there are multiple kernels that support a capability, the kernel
-  with the smaller capability interval will be used. E.g. given:
-  - `KernelA` with `min_capability=80` and `max_capability=89`;
-  - `KernelB` with `min_capability=75` and `max_capability=89`;
-  - `kernelize` runs on a system with capability 8.6.
-
-  Then `KernelA` will be used because the interval 80..89 is smaller
-  than 75..89. The motivation is that kernels with smaller ranges
-  tend to be more optimized for a specific set of GPUs. **This behavior
-  might still change in the future.**
-
-### Registering kernels for specific ROCm capabilities
-
-Registering kernels for the ROCm architecture follows the exact same
-pattern as CUDA kernels, using `min_capability` and `max_capability` to restrict
-a kernel to a range of ROCm capabilities.
-
-### Loading from a local repository for testing
-
-The `LocalLayerRepository` class is provided to load a repository from
-a local directory. For example:
-
-```python
-with use_kernel_mapping(
-    {
-        "SiluAndMul": {
-            "cuda": LocalLayerRepository(
-                repo_path="/home/daniel/kernels/activation",
-                package_name="activation",
-                layer_name="SiluAndMul",
-            )
-        }
-    },
-    inherit_mapping=False,
-):
-    kernelize(linear, mode=Mode.INFERENCE)
-```

flake.lock

@@ -58,32 +58,33 @@
         "nixpkgs": "nixpkgs"
       },
       "locked": {
-        "lastModified": 1754038838,
-        "narHash": "sha256-oHigCT4z0ayyLyEuxdZooSXRAZP8lfOkZHzY1lx1U50=",
+        "lastModified": 1749025620,
+        "narHash": "sha256-V/r5KOp8FRC5n3MINDzTeS3pZz57SasFVzx12WQRQ8U=",
         "owner": "huggingface",
         "repo": "hf-nix",
-        "rev": "336f781fa284e193baa3d4c3ce3f95fb34e9ffad",
+        "rev": "7ab84ffad440c530162f528a96fa062530a6c8e4",
         "type": "github"
       },
       "original": {
         "owner": "huggingface",
+        "ref": "torch-cxx11",
         "repo": "hf-nix",
         "type": "github"
       }
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1752785354,
-        "narHash": "sha256-Y33ryUz7MPqKrZwlbQcsYCUz2jAJCacRf8jbs0tYUlA=",
-        "owner": "nixos",
+        "lastModified": 1747820358,
+        "narHash": "sha256-fTqsZsUX6M3yeEvgyQvXcbGmT2CaRVyVwsi8eK29Oj4=",
+        "owner": "danieldk",
         "repo": "nixpkgs",
-        "rev": "d38025438a6ee456758dc03188ca6873a415463b",
+        "rev": "d3c1681180717528068082103bf323147de6ab0b",
         "type": "github"
       },
       "original": {
-        "owner": "nixos",
+        "owner": "danieldk",
+        "ref": "cudatoolkit-12.9-kernel-builder",
         "repo": "nixpkgs",
-        "rev": "d38025438a6ee456758dc03188ca6873a415463b",
         "type": "github"
       }
     },

flake.nix

@@ -1,6 +1,6 @@
 {
   inputs = {
-    hf-nix.url = "github:huggingface/hf-nix";
+    hf-nix.url = "github:huggingface/hf-nix/torch-cxx11";
     nixpkgs.follows = "hf-nix/nixpkgs";
     flake-utils.url = "github:numtide/flake-utils";
   };
@@ -16,7 +16,7 @@
       let
         pkgs = import nixpkgs {
           inherit system;
-          config = hf-nix.lib.config system;
+          inherit (hf-nix.lib) config;
           overlays = [
             hf-nix.overlays.default
           ];
@@ -26,10 +26,6 @@
         formatter = pkgs.nixfmt-tree;
         devShells = with pkgs; rec {
           default = mkShell {
-            nativeBuildInputs = [
-              # For hf-doc-builder.
-              nodejs
-            ];
             buildInputs =
               [
                 black
@@ -40,7 +36,6 @@
               ++ (with python3.pkgs; [
                 docutils
                 huggingface-hub
-                mktestdocs
                 pytest
                 pytest-benchmark
                 pyyaml

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "kernels"
-version = "0.10.1.dev0"
+version = "0.6.1"
 description = "Download compute kernels"
 authors = [
   { name = "OlivierDehaene", email = "olivier@huggingface.co" },
@@ -24,20 +24,16 @@ build-backend = "setuptools.build_meta"
 
 [dependency-groups]
 dev = [
-  "mktestdocs>=0.2.5",
-  "mypy>=1.15.0",
-  "pytest>=8",
+  "mypy == 1.14.1",
+  "pytest >=8",
   # Whatever version is compatible with pytest.
   "pytest-benchmark",
-  "torch>=2.5",
+  "torch >=2.5",
   "types-pyyaml"
 ]
 
 [project.optional-dependencies]
 torch = ["torch"]
-docs = [
-  "hf-doc-builder",
-]
 
 [project.scripts]
 kernels = "kernels.cli:main"

pytest.ini

@@ -1,7 +1,4 @@
 [pytest]
 markers =
-    cuda_only: marks tests that should only hosts with CUDA GPUs
-    rocm_only: marks tests that should only run on hosts with ROCm GPUs
     darwin_only: marks tests that should only run on macOS
-    xpu_only: marks tests that should only run on hosts with Intel XPUs
-    token: enable tests that require a write token
+    linux_only: marks tests that should only run on Linux

src/kernels/__init__.py

@@ -1,14 +1,6 @@
-import importlib.metadata
-
-__version__ = importlib.metadata.version("kernels")
-
 from kernels.layer import (
-    CUDAProperties,
     Device,
     LayerRepository,
-    LocalLayerRepository,
-    LockedLayerRepository,
-    Mode,
     kernelize,
     register_kernel_mapping,
     replace_kernel_forward_from_hub,
@@ -17,7 +9,6 @@ from kernels.layer import (
 )
 from kernels.utils import (
     get_kernel,
-    get_local_kernel,
     get_locked_kernel,
     has_kernel,
     install_kernel,
@@ -25,22 +16,16 @@ from kernels.utils import (
 )
 
 __all__ = [
-    "__version__",
-    "CUDAProperties",
-    "Device",
-    "LayerRepository",
-    "LocalLayerRepository",
-    "LockedLayerRepository",
-    "Mode",
     "get_kernel",
-    "get_local_kernel",
     "get_locked_kernel",
     "has_kernel",
-    "install_kernel",
-    "kernelize",
     "load_kernel",
-    "register_kernel_mapping",
-    "replace_kernel_forward_from_hub",
+    "install_kernel",
     "use_kernel_forward_from_hub",
     "use_kernel_mapping",
+    "register_kernel_mapping",
+    "replace_kernel_forward_from_hub",
+    "LayerRepository",
+    "Device",
+    "kernelize",
 ]

src/kernels/_interval_tree.py

@@ -1,200 +0,0 @@
-# AVL-balanced interval trees. We could use the intervaltree
-# packages, but it seems unmaintained and does not have type
-# annotations.
-
-from typing import Generic, List, Optional, Tuple, TypeVar
-
-T = TypeVar("T")
-
-
-class _Node(Generic[T]):
-    """A node in the interval tree."""
-
-    def __init__(self, start: int, end: int, data: T):
-        self.start: int = start
-        self.end: int = end
-        self.data: T = data
-        self.max_end: int = end
-        self.left: Optional["_Node[T]"] = None
-        self.right: Optional["_Node[T]"] = None
-        self.height: int = 1
-
-    def __repr__(self) -> str:
-        return f"Node({self.start}, {self.end})"
-
-
-class IntervalTree(Generic[T]):
-    """A data structure to hold and query (unique) intervals."""
-
-    root: Optional[_Node[T]]
-
-    def __init__(self):
-        self.root = None
-
-    def insert(self, start: int, end: int, data: T) -> None:
-        """
-        Inserts a new interval into the tree.
-
-        Args:
-            start: The starting point of the interval.
-            end: The ending point of the interval.
-            data: The data associated with this interval.
-        """
-        self.root = self._insert(self.root, start, end, data)
-
-    def _get_height(self, node: Optional[_Node[T]]) -> int:
-        if not node:
-            return 0
-        return node.height
-
-    def _get_balance(self, node: Optional[_Node[T]]) -> int:
-        if not node:
-            return 0
-        return self._get_height(node.left) - self._get_height(node.right)
-
-    def _update_node_attributes(self, node: _Node[T]) -> None:
-        node.height = 1 + max(self._get_height(node.left), self._get_height(node.right))
-        node.max_end = node.end
-        if node.left:
-            node.max_end = max(node.max_end, node.left.max_end)
-        if node.right:
-            node.max_end = max(node.max_end, node.right.max_end)
-
-    def _right_rotate(self, y: _Node[T]) -> _Node[T]:
-        """Performs a right rotation."""
-        x = y.left
-        assert x is not None
-        T2 = x.right
-
-        x.right = y
-        y.left = T2
-
-        self._update_node_attributes(y)
-        self._update_node_attributes(x)
-
-        return x
-
-    def _left_rotate(self, x: _Node[T]) -> _Node[T]:
-        """Performs a left rotation."""
-        y = x.right
-        assert y is not None
-        T2 = y.left
-
-        y.left = x
-        x.right = T2
-
-        self._update_node_attributes(x)
-        self._update_node_attributes(y)
-
-        return y
-
-    def _insert(
-        self, node: Optional[_Node[T]], start: int, end: int, data: T
-    ) -> _Node[T]:
-        """Recursive helper to insert a new node and balance the tree."""
-        if not node:
-            return _Node(start, end, data)
-
-        # Replace the data if the interval already exists.
-        if start == node.start and end == node.end:
-            node.data = data
-            return node
-
-        if start < node.start:
-            node.left = self._insert(node.left, start, end, data)
-        else:
-            node.right = self._insert(node.right, start, end, data)
-
-        self._update_node_attributes(node)
-
-        balance = self._get_balance(node)
-
-        # Left Left Case
-        if balance > 1 and node.left and start < node.left.start:
-            return self._right_rotate(node)
-
-        # Right Right Case
-        if balance < -1 and node.right and start >= node.right.start:
-            return self._left_rotate(node)
-
-        # Left Right Case
-        if balance > 1 and node.left and start >= node.left.start:
-            node.left = self._left_rotate(node.left)
-            return self._right_rotate(node)
-
-        # Right Left Case
-        if balance < -1 and node.right and start < node.right.start:
-            node.right = self._right_rotate(node.right)
-            return self._left_rotate(node)
-
-        return node
-
-    def search(self, point: int) -> List[T]:
-        """
-        Searches for all intervals that contain the given point.
-
-        Args:
-            point: The point to search for.
-
-        Returns:
-            A list of data items from all matching intervals.
-        """
-        results: List[T] = []
-        self._search(self.root, point, results)
-        return results
-
-    def _search(self, node: Optional[_Node[T]], point: int, results: List[T]) -> None:
-        """Recursive helper to find all overlapping intervals."""
-        if node is None or point > node.max_end:
-            return
-
-        if node.left:
-            self._search(node.left, point, results)
-
-        if node.start <= point <= node.end:
-            results.append(node.data)
-
-        if point >= node.start and node.right:
-            self._search(node.right, point, results)
-
-    def find_smallest_interval(self, point: int) -> Optional[T]:
-        """
-        Finds the item with the most specific (smallest) range for a given point.
-
-        Args:
-            point: The capability to look up.
-
-        Returns:
-            The data of the best-matching item, or None if no match is found.
-        """
-        matches: List[Tuple[int, int, T]] = []
-        self._find_with_intervals(self.root, point, matches)
-
-        if not matches:
-            return None
-
-        # Return the smallest interval, sort by memory location when
-        # there are multiple matches with the same interval size. This
-        # is just to ensure that we can compare against a trivial
-        # implementation in tests.
-        best_match = min(matches, key=lambda x: (x[1] - x[0], id(x[2])))
-        return best_match[2]
-
-    def _find_with_intervals(
-        self,
-        node: Optional[_Node[T]],
-        point: int,
-        results: List[Tuple[int, int, T]],
-    ) -> None:
-        """A modified search that collects interval ranges along with data."""
-        if node is None or point > node.max_end:
-            return
-
-        if node.left:
-            self._find_with_intervals(node.left, point, results)
-
-        if node.start <= point <= node.end:
-            results.append((node.start, node.end, node.data))
-
-        if point >= node.start and node.right:
-            self._find_with_intervals(node.right, point, results)

src/kernels/_versions.py

@@ -1,52 +0,0 @@
-from typing import Dict, Optional
-
-from huggingface_hub import HfApi
-from huggingface_hub.hf_api import GitRefInfo
-from packaging.specifiers import SpecifierSet
-from packaging.version import InvalidVersion, Version
-
-
-def _get_available_versions(repo_id: str) -> Dict[Version, GitRefInfo]:
-    """Get kernel versions that are available in the repository."""
-    versions = {}
-    for tag in HfApi().list_repo_refs(repo_id).tags:
-        if not tag.name.startswith("v"):
-            continue
-        try:
-            versions[Version(tag.name[1:])] = tag
-        except InvalidVersion:
-            continue
-
-    return versions
-
-
-def resolve_version_spec_as_ref(repo_id: str, version_spec: str) -> GitRefInfo:
-    """
-    Get the locks for a kernel with the given version spec.
-
-    The version specifier can be any valid Python version specifier:
-    https://packaging.python.org/en/latest/specifications/version-specifiers/#version-specifiers
-    """
-    versions = _get_available_versions(repo_id)
-    requirement = SpecifierSet(version_spec)
-    accepted_versions = sorted(requirement.filter(versions.keys()))
-
-    if len(accepted_versions) == 0:
-        raise ValueError(
-            f"No version of `{repo_id}` satisfies requirement: {version_spec}"
-        )
-
-    return versions[accepted_versions[-1]]
-
-
-def select_revision_or_version(
-    repo_id: str, revision: Optional[str], version: Optional[str]
-) -> str:
-    if revision is not None and version is not None:
-        raise ValueError("Either a revision or a version must be specified, not both.")
-    elif revision is None and version is None:
-        revision = "main"
-    elif version is not None:
-        revision = resolve_version_spec_as_ref(repo_id, version).target_commit
-    assert revision is not None
-    return revision

src/kernels/cli.py

@@ -4,8 +4,6 @@ import json
 import sys
 from pathlib import Path
 
-from huggingface_hub import create_repo, upload_folder
-
 from kernels.compat import tomllib
 from kernels.lockfile import KernelLock, get_kernel_locks
 from kernels.utils import install_kernel, install_kernel_all_variants
@@ -33,24 +31,6 @@ def main():
     )
     download_parser.set_defaults(func=download_kernels)
 
-    upload_parser = subparsers.add_parser("upload", help="Upload kernels to the Hub")
-    upload_parser.add_argument(
-        "kernel_dir",
-        type=Path,
-        help="Directory of the kernel build",
-    )
-    upload_parser.add_argument(
-        "--repo_id",
-        type=str,
-        help="Repository ID to use to upload to the Hugging Face Hub",
-    )
-    upload_parser.add_argument(
-        "--private",
-        action="store_true",
-        help="If the repository should be private.",
-    )
-    upload_parser.set_defaults(func=upload_kernels)
-
     lock_parser = subparsers.add_parser("lock", help="Lock kernel revisions")
     lock_parser.add_argument(
         "project_dir",
@@ -173,33 +153,6 @@ def lock_kernels(args):
         json.dump(all_locks, f, cls=_JSONEncoder, indent=2)
 
 
-def upload_kernels(args):
-    kernel_dir = Path(args.kernel_dir).resolve()
-    build_dir = kernel_dir / "build"
-    if not kernel_dir.is_dir():
-        raise ValueError(f"{kernel_dir} is not a directory")
-    if not build_dir.is_dir():
-        raise ValueError("Couldn't find `build` directory inside `kernel_dir`")
-
-    repo_id = create_repo(
-        repo_id=args.repo_id, private=args.private, exist_ok=True
-    ).repo_id
-
-    delete_patterns: set[str] = set()
-    for build_variant in build_dir.iterdir():
-        if build_variant.is_dir():
-            delete_patterns.add(f"{build_variant.name}/**")
-
-    upload_folder(
-        repo_id=repo_id,
-        folder_path=build_dir,
-        path_in_repo="build",
-        delete_patterns=list(delete_patterns),
-        commit_message="Build uploaded using `kernels`.",
-    )
-    print(f"✅ Kernel upload successful. Find the kernel in https://hf.co/{repo_id}.")
-
-
 class _JSONEncoder(json.JSONEncoder):
     def default(self, o):
         if dataclasses.is_dataclass(o):

src/kernels/lockfile.py

@@ -4,8 +4,10 @@ from pathlib import Path
 from typing import Dict, List, Tuple
 
 from huggingface_hub import HfApi
+from huggingface_hub.hf_api import GitRefInfo
+from packaging.specifiers import SpecifierSet
+from packaging.version import InvalidVersion, Version
 
-from kernels._versions import resolve_version_spec_as_ref
 from kernels.compat import tomllib
 
 
@@ -29,6 +31,20 @@ class KernelLock:
         return cls(repo_id=o["repo_id"], sha=o["sha"], variants=variants)
 
 
+def _get_available_versions(repo_id: str) -> Dict[Version, GitRefInfo]:
+    """Get kernel versions that are available in the repository."""
+    versions = {}
+    for tag in HfApi().list_repo_refs(repo_id).tags:
+        if not tag.name.startswith("v"):
+            continue
+        try:
+            versions[Version(tag.name[1:])] = tag
+        except InvalidVersion:
+            continue
+
+    return versions
+
+
 def get_kernel_locks(repo_id: str, version_spec: str) -> KernelLock:
     """
     Get the locks for a kernel with the given version spec.
@@ -36,7 +52,16 @@ def get_kernel_locks(repo_id: str, version_spec: str) -> KernelLock:
     The version specifier can be any valid Python version specifier:
     https://packaging.python.org/en/latest/specifications/version-specifiers/#version-specifiers
     """
-    tag_for_newest = resolve_version_spec_as_ref(repo_id, version_spec)
+    versions = _get_available_versions(repo_id)
+    requirement = SpecifierSet(version_spec)
+    accepted_versions = sorted(requirement.filter(versions.keys()))
+
+    if len(accepted_versions) == 0:
+        raise ValueError(
+            f"No version of `{repo_id}` satisfies requirement: {version_spec}"
+        )
+
+    tag_for_newest = versions[accepted_versions[-1]]
 
     r = HfApi().repo_info(
         repo_id=repo_id, revision=tag_for_newest.target_commit, files_metadata=True

src/kernels/utils.py

@@ -16,7 +16,6 @@ from typing import Dict, List, Optional, Tuple
 from huggingface_hub import file_exists, snapshot_download
 from packaging.version import parse
 
-from kernels._versions import select_revision_or_version
 from kernels.lockfile import KernelLock, VariantLock
 
 
@@ -46,12 +45,9 @@ def build_variant() -> str:
         compute_framework = f"rocm{rocm_version.major}{rocm_version.minor}"
     elif torch.backends.mps.is_available():
         compute_framework = "metal"
-    elif torch.version.xpu is not None:
-        version = torch.version.xpu
-        compute_framework = f"xpu{version[0:4]}{version[5:6]}"
     else:
         raise AssertionError(
-            "Torch was not compiled with CUDA, Metal, XPU, or ROCm enabled."
+            "Torch was not compiled with CUDA, Metal, or ROCm enabled."
         )
 
     torch_version = parse(torch.__version__)
@@ -59,7 +55,6 @@ def build_variant() -> str:
     os = platform.system().lower()
 
     if os == "darwin":
-        cpu = "aarch64" if cpu == "arm64" else cpu
         return f"torch{torch_version.major}{torch_version.minor}-{compute_framework}-{cpu}-{os}"
 
     cxxabi = "cxx11" if torch.compiled_with_cxx11_abi() else "cxx98"
@@ -99,20 +94,7 @@ def install_kernel(
     """
     Download a kernel for the current environment to the cache.
 
-    The output path is validated against the hashes in `variant_locks` when provided.
-
-    Args:
-        repo_id (`str`):
-            The Hub repository containing the kernel.
-        revision (`str`):
-            The specific revision (branch, tag, or commit) to download.
-        local_files_only (`bool`, *optional*, defaults to `False`):
-            Whether to only use local files and not download from the Hub.
-        variant_locks (`Dict[str, VariantLock]`, *optional*):
-            Optional dictionary of variant locks for validation.
-
-    Returns:
-        `Tuple[str, Path]`: A tuple containing the package name and the path to the variant directory.
+    The output path is validated againt `hash` when set.
     """
     package_name = package_name_from_repo_id(repo_id)
     variant = build_variant()
@@ -127,23 +109,6 @@ def install_kernel(
         )
     )
 
-    try:
-        return _load_kernel_from_path(repo_path, package_name, variant_locks)
-    except FileNotFoundError:
-        # Redo with more specific error message.
-        raise FileNotFoundError(
-            f"Kernel `{repo_id}` at revision {revision} does not have build: {variant}"
-        )
-
-
-def _load_kernel_from_path(
-    repo_path: Path,
-    package_name: str,
-    variant_locks: Optional[Dict[str, VariantLock]] = None,
-) -> Tuple[str, Path]:
-    variant = build_variant()
-    universal_variant = universal_build_variant()
-
     variant_path = repo_path / "build" / variant
     universal_variant_path = repo_path / "build" / universal_variant
 
@@ -162,7 +127,7 @@ def _load_kernel_from_path(
 
     if not os.path.exists(module_init_path):
         raise FileNotFoundError(
-            f"Kernel at path `{repo_path}` does not have build: {variant}"
+            f"Kernel `{repo_id}` at revision {revision} does not have build: {variant}"
         )
 
     return package_name, variant_path
@@ -199,96 +164,16 @@ def install_kernel_all_variants(
     return repo_path / "build"
 
 
-def get_kernel(
-    repo_id: str, revision: Optional[str] = None, version: Optional[str] = None
-) -> ModuleType:
-    """
-    Load a kernel from the kernel hub.
-
-    This function downloads a kernel to the local Hugging Face Hub cache directory (if it was not downloaded before)
-    and then loads the kernel.
-
-    Args:
-        repo_id (`str`):
-            The Hub repository containing the kernel.
-        revision (`str`, *optional*, defaults to `"main"`):
-            The specific revision (branch, tag, or commit) to download. Cannot be used together with `version`.
-        version (`str`, *optional*):
-            The kernel version to download. This can be a Python version specifier, such as `">=1.0.0,<2.0.0"`.
-            Cannot be used together with `revision`.
-
-    Returns:
-        `ModuleType`: The imported kernel module.
-
-    Example:
-        ```python
-        import torch
-        from kernels import get_kernel
-
-        activation = get_kernel("kernels-community/activation")
-        x = torch.randn(10, 20, device="cuda")
-        out = torch.empty_like(x)
-        result = activation.silu_and_mul(out, x)
-        ```
-    """
-    revision = select_revision_or_version(repo_id, revision, version)
+def get_kernel(repo_id: str, revision: str = "main") -> ModuleType:
     package_name, package_path = install_kernel(repo_id, revision=revision)
     return import_from_path(package_name, package_path / package_name / "__init__.py")
 
 
-def get_local_kernel(repo_path: Path, package_name: str) -> ModuleType:
+def has_kernel(repo_id: str, revision: str = "main") -> bool:
     """
-    Import a kernel from a local kernel repository path.
-
-    Args:
-        repo_path (`Path`):
-            The local path to the kernel repository.
-        package_name (`str`):
-            The name of the package to import from the repository.
-
-    Returns:
-        `ModuleType`: The imported kernel module.
+    Check whether a kernel build exists for the current environment
+    (Torch version and compute framework).
     """
-    variant = build_variant()
-    universal_variant = universal_build_variant()
-
-    # Presume we were given the top level path of the kernel repository.
-    for base_path in [repo_path, repo_path / "build"]:
-        # Prefer the universal variant if it exists.
-        for v in [universal_variant, variant]:
-            package_path = base_path / v / package_name / "__init__.py"
-            if package_path.exists():
-                return import_from_path(package_name, package_path)
-
-    # If we didn't find the package in the repo we may have a explicit
-    # package path.
-    package_path = repo_path / package_name / "__init__.py"
-    if package_path.exists():
-        return import_from_path(package_name, package_path)
-
-    raise FileNotFoundError(f"Could not find package '{package_name}' in {repo_path}")
-
-
-def has_kernel(
-    repo_id: str, revision: Optional[str] = None, version: Optional[str] = None
-) -> bool:
-    """
-    Check whether a kernel build exists for the current environment (Torch version and compute framework).
-
-    Args:
-        repo_id (`str`):
-            The Hub repository containing the kernel.
-        revision (`str`, *optional*, defaults to `"main"`):
-            The specific revision (branch, tag, or commit) to download. Cannot be used together with `version`.
-        version (`str`, *optional*):
-            The kernel version to download. This can be a Python version specifier, such as `">=1.0.0,<2.0.0"`.
-            Cannot be used together with `revision`.
-
-    Returns:
-        `bool`: `True` if a kernel is available for the current environment.
-    """
-    revision = select_revision_or_version(repo_id, revision, version)
-
     package_name = package_name_from_repo_id(repo_id)
     variant = build_variant()
     universal_variant = universal_build_variant()
@@ -311,16 +196,8 @@ def load_kernel(repo_id: str, *, lockfile: Optional[Path] = None) -> ModuleType:
     """
     Get a pre-downloaded, locked kernel.
 
-    If `lockfile` is not specified, the lockfile will be loaded from the caller's package metadata.
-
-    Args:
-        repo_id (`str`):
-            The Hub repository containing the kernel.
-        lockfile (`Path`, *optional*):
-            Path to the lockfile. If not provided, the lockfile will be loaded from the caller's package metadata.
-
-    Returns:
-        `ModuleType`: The imported kernel module.
+    If `lockfile` is not specified, the lockfile will be loaded from the
+    caller's package metadata.
     """
     if lockfile is None:
         locked_sha = _get_caller_locked_kernel(repo_id)
@@ -365,18 +242,7 @@ def load_kernel(repo_id: str, *, lockfile: Optional[Path] = None) -> ModuleType:
 
 
 def get_locked_kernel(repo_id: str, local_files_only: bool = False) -> ModuleType:
-    """
-    Get a kernel using a lock file.
-
-    Args:
-        repo_id (`str`):
-            The Hub repository containing the kernel.
-        local_files_only (`bool`, *optional*, defaults to `False`):
-            Whether to only use local files and not download from the Hub.
-
-    Returns:
-        `ModuleType`: The imported kernel module.
-    """
+    """Get a kernel using a lock file."""
     locked_sha = _get_caller_locked_kernel(repo_id)
 
     if locked_sha is None:

tests/conftest.py

@@ -1,41 +1,10 @@
 import sys
 
 import pytest
-import torch
-
-has_cuda = (
-    hasattr(torch.version, "cuda")
-    and torch.version.cuda is not None
-    and torch.cuda.device_count() > 0
-)
-has_rocm = (
-    hasattr(torch.version, "hip")
-    and torch.version.hip is not None
-    and torch.cuda.device_count() > 0
-)
-has_xpu = (
-    hasattr(torch.version, "xpu")
-    and torch.version.xpu is not None
-    and torch.xpu.device_count() > 0
-)
-
-
-def pytest_addoption(parser):
-    parser.addoption(
-        "--token",
-        action="store_true",
-        help="run tests that require a token with write permissions",
-    )
 
 
 def pytest_runtest_setup(item):
-    if "cuda_only" in item.keywords and not has_cuda:
-        pytest.skip("skipping CUDA-only test on host without CUDA")
-    if "rocm_only" in item.keywords and not has_rocm:
-        pytest.skip("skipping ROCm-only test on host without ROCm")
+    if "linux_only" in item.keywords and not sys.platform.startswith("linux"):
+        pytest.skip("skipping Linux-only test on non-Linux platform")
     if "darwin_only" in item.keywords and not sys.platform.startswith("darwin"):
         pytest.skip("skipping macOS-only test on non-macOS platform")
-    if "xpu_only" in item.keywords and not has_xpu:
-        pytest.skip("skipping XPU-only test on host without XPU")
-    if "token" in item.keywords and not item.config.getoption("--token"):
-        pytest.skip("need --token option to run this test")

tests/layer_locking/kernels.lock

@@ -1,12 +0,0 @@
-[
-  {
-    "repo_id": "kernels-test/versions",
-    "sha": "dc142fd6c9920c993d32be6358b78957c58681c3",
-    "variants": {
-      "torch-universal": {
-        "hash": "sha256-35ce0ccfe68e392cbc06feef72268f4c41a74b9920496a2c6ee8978db7f7c17c",
-        "hash_type": "git_lfs_concat"
-      }
-    }
-  }
-]

tests/layer_locking/pyproject.toml

@@ -1,2 +0,0 @@
-[tool.kernels.dependencies]
-"kernels-test/versions" = ">=0.1.0,<0.2.0"

tests/test_basic.py

@@ -1,7 +1,7 @@
 import pytest
 import torch
 
-from kernels import get_kernel, get_local_kernel, has_kernel, install_kernel
+from kernels import get_kernel, has_kernel
 
 
 @pytest.fixture
@@ -9,20 +9,6 @@ def kernel():
     return get_kernel("kernels-community/activation")
 
 
-@pytest.fixture
-def local_kernel_path():
-    package_name, path = install_kernel("kernels-community/activation", "main")
-    # Path is the build variant path (build/torch-<...>), so the grandparent
-    # is the kernel repository path.
-    return package_name, path
-
-
-@pytest.fixture
-def local_kernel(local_kernel_path):
-    package_name, path = local_kernel_path
-    return get_local_kernel(path.parent.parent, package_name)
-
-
 @pytest.fixture
 def metal_kernel():
     return get_kernel("kernels-test/relu-metal")
@@ -40,7 +26,7 @@ def device():
     return "cuda"
 
 
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 def test_gelu_fast(kernel, device):
     x = torch.arange(1, 10, dtype=torch.float16, device=device).view(3, 3)
     y = torch.empty_like(x)
@@ -56,55 +42,6 @@ def test_gelu_fast(kernel, device):
     assert torch.allclose(y, expected)
 
 
-@pytest.mark.cuda_only
-def test_local_kernel(local_kernel, device):
-    x = torch.arange(1, 10, dtype=torch.float16, device=device).view(3, 3)
-    y = torch.empty_like(x)
-
-    local_kernel.gelu_fast(y, x)
-
-    expected = torch.tensor(
-        [[0.8408, 1.9551, 2.9961], [4.0000, 5.0000, 6.0000], [7.0000, 8.0000, 9.0000]],
-        device=device,
-        dtype=torch.float16,
-    )
-
-    assert torch.allclose(y, expected)
-
-
-@pytest.mark.cuda_only
-def test_local_kernel_path_types(local_kernel_path, device):
-    package_name, path = local_kernel_path
-
-    # Top-level repo path
-    # ie: /home/ubuntu/.cache/huggingface/hub/models--kernels-community--activation/snapshots/2fafa6a3a38ccb57a1a98419047cf7816ecbc071
-    kernel = get_local_kernel(path.parent.parent, package_name)
-    x = torch.arange(1, 10, dtype=torch.float16, device=device).view(3, 3)
-    y = torch.empty_like(x)
-
-    kernel.gelu_fast(y, x)
-    expected = torch.tensor(
-        [[0.8408, 1.9551, 2.9961], [4.0000, 5.0000, 6.0000], [7.0000, 8.0000, 9.0000]],
-        device=device,
-        dtype=torch.float16,
-    )
-    assert torch.allclose(y, expected)
-
-    # Build directory path
-    # ie: /home/ubuntu/.cache/huggingface/hub/models--kernels-community--activation/snapshots/2fafa6a3a38ccb57a1a98419047cf7816ecbc071/build
-    kernel = get_local_kernel(path.parent.parent / "build", package_name)
-    y = torch.empty_like(x)
-    kernel.gelu_fast(y, x)
-    assert torch.allclose(y, expected)
-
-    # Explicit package path
-    # ie: /home/ubuntu/.cache/huggingface/hub/models--kernels-community--activation/snapshots/2fafa6a3a38ccb57a1a98419047cf7816ecbc071/build/torch28-cxx11-cu128-x86_64-linux
-    kernel = get_local_kernel(path, package_name)
-    y = torch.empty_like(x)
-    kernel.gelu_fast(y, x)
-    assert torch.allclose(y, expected)
-
-
 @pytest.mark.darwin_only
 @pytest.mark.parametrize("dtype", [torch.float16, torch.float32])
 def test_relu_metal(metal_kernel, dtype):
@@ -113,7 +50,7 @@ def test_relu_metal(metal_kernel, dtype):
     assert torch.allclose(y, torch.relu(x))
 
 
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 @pytest.mark.parametrize(
     "kernel_exists",
     [
@@ -130,26 +67,7 @@ def test_has_kernel(kernel_exists):
     assert has_kernel(repo_id, revision=revision) == kernel
 
 
-def test_version():
-    kernel = get_kernel("kernels-test/versions")
-    assert kernel.version() == "0.2.0"
-    kernel = get_kernel("kernels-test/versions", version="<1.0.0")
-    assert kernel.version() == "0.2.0"
-    kernel = get_kernel("kernels-test/versions", version="<0.2.0")
-    assert kernel.version() == "0.1.1"
-    kernel = get_kernel("kernels-test/versions", version=">0.1.0,<0.2.0")
-    assert kernel.version() == "0.1.1"
-
-    with pytest.raises(ValueError, match=r"No version.*satisfies requirement"):
-        get_kernel("kernels-test/versions", version=">0.2.0")
-
-    with pytest.raises(ValueError, match=r"Either a revision or a version.*not both"):
-        kernel = get_kernel(
-            "kernels-test/versions", revision="v0.1.0", version="<1.0.0"
-        )
-
-
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 def test_universal_kernel(universal_kernel):
     torch.manual_seed(0)
     A = torch.randint(-10, 10, (64, 128), dtype=torch.int8, device="cuda")

tests/test_benchmarks.py

@@ -16,21 +16,21 @@ def device():
     return "cuda"
 
 
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 def test_gelu_small(kernel, device, benchmark):
     x = torch.randn(32, 32, dtype=torch.float16, device=device)
     y = torch.empty_like(x)
     benchmark(kernel.gelu_fast, y, x)
 
 
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 def test_gelu_medium(kernel, device, benchmark):
     x = torch.randn(128, 128, dtype=torch.float16, device=device)
     y = torch.empty_like(x)
     benchmark(kernel.gelu_fast, y, x)
 
 
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 def test_gelu_large(kernel, device, benchmark):
     x = torch.randn(512, 512, dtype=torch.float16, device=device)
     y = torch.empty_like(x)

tests/test_doctest.py

@@ -1,49 +0,0 @@
-import inspect
-
-import pytest
-from mktestdocs import check_docstring, get_codeblock_members
-
-import kernels
-
-
-def all_public_functions():
-    function_list = inspect.getmembers(kernels, inspect.isfunction)
-    return [func for _, func in function_list]
-
-
-def all_public_classes():
-    class_list = inspect.getmembers(kernels, inspect.isclass)
-    return [cls for _, cls in class_list]
-
-
-def all_public_class_members():
-    members = get_codeblock_members(*all_public_classes())
-    return members
-
-
-@pytest.mark.cuda_only
-@pytest.mark.parametrize(
-    "func",
-    all_public_functions(),
-    ids=lambda d: d.__name__,
-)
-def test_func_docstring(func):
-    check_docstring(obj=func)
-
-
-@pytest.mark.cuda_only
-@pytest.mark.parametrize(
-    "cls",
-    all_public_classes(),
-    ids=lambda d: d.__name__,
-)
-def test_class_docstring(cls):
-    check_docstring(obj=cls)
-
-
-@pytest.mark.cuda_only
-@pytest.mark.parametrize(
-    "member", all_public_class_members(), ids=lambda d: d.__qualname__
-)
-def test_member_docstring(member):
-    check_docstring(member)

tests/test_interval_tree.py

@@ -1,230 +0,0 @@
-import random
-from typing import Generic, List, Optional, Tuple, TypeVar
-
-import pytest
-
-from kernels._interval_tree import IntervalTree, _Node
-
-T = TypeVar("T")
-
-
-class SimpleIntervalStore(Generic[T]):
-    """A simple O(n) implementation that stores intervals in a list."""
-
-    def __init__(self):
-        self.intervals: List[Tuple[int, int, T]] = []
-
-    def insert(self, start: int, end: int, data: T) -> None:
-        """Insert an interval into the store."""
-        # Replace data if the interval already exists.
-        for i, (existing_start, existing_end, existing_data) in enumerate(
-            self.intervals
-        ):
-            if existing_start == start and existing_end == end:
-                self.intervals[i] = (start, end, data)
-                return
-
-        self.intervals.append((start, end, data))
-
-    def find_smallest_interval(self, point: int) -> Optional[T]:
-        """Find the best match using linear search."""
-        matches = []
-        for start, end, data in self.intervals:
-            if start <= point <= end:
-                matches.append((start, end, data))
-
-        if not matches:
-            return None
-
-        # Return the smallest interval, sort by memory location when
-        # there are multiple matches with the same interval size. This
-        # mirrors the ordering in the intervan tree.
-        best_match = min(matches, key=lambda x: (x[1] - x[0], id(x[2])))
-        return best_match[2]
-
-
-def is_balanced(tree: IntervalTree[T]) -> bool:
-    """Check if the AVL tree is properly balanced."""
-
-    def check_balance(node: Optional[_Node[T]]) -> Tuple[bool, int]:
-        if node is None:
-            return True, 0
-
-        # Left and right subtrees should be balanced.
-        left_balanced, left_height = check_balance(node.left)
-        if not left_balanced:
-            return False, -1
-
-        right_balanced, right_height = check_balance(node.right)
-        if not right_balanced:
-            return False, -1
-
-        # The difference in height should not exceed 1.
-        if abs(left_height - right_height) > 1:
-            return False, -1
-
-        # Check if the height is correct.
-        expected_height = 1 + max(left_height, right_height)
-        if node.height != expected_height:
-            return False, -1
-
-        return True, expected_height
-
-    balanced, _ = check_balance(tree.root)
-    return balanced
-
-
-@pytest.fixture
-def populated_tree() -> IntervalTree[str]:
-    """Provides a pre-populated IntervalTree for testing."""
-    tree = IntervalTree[str]()
-    kernels = [
-        (80, 89, "Kernel_A_General_80_89"),
-        (86, 89, "Kernel_B_Ampere_86_89"),
-        (80, 86, "Kernel_C_Older_Ampere_80_86"),
-        (70, 75, "Kernel_D_Volta_70_75"),
-        (86, 87, "Kernel_E_Specific_86_87"),
-    ]
-    for start, end, name in kernels:
-        tree.insert(start, end, name)
-    return tree
-
-
-def test_find_smallest_interval_match_with_multiple_overlaps(populated_tree):
-    # Check that the smallest inteval is selected when there are
-    # multiple matching intervals.
-    assert populated_tree.find_smallest_interval(86) == "Kernel_E_Specific_86_87"
-
-
-def test_find_single_match(populated_tree):
-    assert populated_tree.find_smallest_interval(72) == "Kernel_D_Volta_70_75"
-    assert populated_tree.find_smallest_interval(75) == "Kernel_D_Volta_70_75"
-
-
-def test_no_match_outside_all_ranges(populated_tree):
-    # Check that no interval is found when the value is out of range
-    # (too small/too large).
-    assert populated_tree.find_smallest_interval(65) is None
-    assert populated_tree.find_smallest_interval(95) is None
-
-
-def test_no_match_in_gap_between_ranges(populated_tree):
-    # Check that no interval is found when the value is between two
-    # intervals.
-    assert populated_tree.find_smallest_interval(78) is None
-
-
-def test_boundary_conditions_start_and_end(populated_tree):
-    # Test exact upper/lower bounds of intervals.
-    assert populated_tree.find_smallest_interval(80) == "Kernel_C_Older_Ampere_80_86"
-    assert populated_tree.find_smallest_interval(89) == "Kernel_B_Ampere_86_89"
-
-
-def test_empty_tree():
-    # Searching in an empty tree should return None.
-    empty_tree = IntervalTree[str]()
-    assert empty_tree.find_smallest_interval(100) is None
-
-
-def test_multiple_equally_specific_matches():
-    # Check that we pick the match in a stable way when there is are
-    # multiple matching intervals with the same size.
-    tree = IntervalTree[str]()
-    str1 = "First_Narrow_Kernel"
-    str2 = "Second_Narrow_Kernel"
-    tree.insert(10, 20, "Wide_Kernel")
-    tree.insert(12, 17, str1)
-    tree.insert(14, 19, str2)
-
-    if id(str1) < id(str2):
-        assert tree.find_smallest_interval(15) == str1
-    else:
-        assert tree.find_smallest_interval(15) == str2
-
-
-def test_property_based_interval_tree():
-    # Quick-check property-based testing:
-    #
-    # - Verify that the tree is balanced after each insertion.
-    # - Verify the query against a simple list-based implementation.
-
-    random.seed(42)  # For reproducible tests
-
-    test_points = list(range(0, 101))
-
-    for _ in range(5):
-        tree = IntervalTree[str]()
-        simple = SimpleIntervalStore[str]()
-
-        intervals = []
-        for i in range(100):
-            start = random.randint(0, 90)
-            end = random.randint(start, 100)
-            data = f"interval_{i}_s{start}_e{end}"
-            intervals.append((start, end, data))
-
-        for i, (start, end, data) in enumerate(intervals):
-            tree.insert(start, end, data)
-            simple.insert(start, end, data)
-
-            # Check that tree is still balanced
-            assert is_balanced(
-                tree
-            ), f"Tree became unbalanced after inserting interval {i}: ({start}, {end})"
-
-            for point in test_points:
-                tree_result = tree.find_smallest_interval(point)
-                simple_result = simple.find_smallest_interval(point)
-
-                assert tree_result == simple_result, (
-                    f"Mismatch for point {point} after inserting {i+1} intervals. "
-                    f"Tree: {tree_result}, Simple: {simple_result}. "
-                    f"Last inserted: ({start}, {end})"
-                )
-
-
-def test_property_based_edge_cases():
-    random.seed(123)
-
-    tree = IntervalTree[str]()
-    simple = SimpleIntervalStore[str]()
-
-    # Single-point intervals.
-    for i in range(10):
-        point = random.randint(0, 100)
-        data = f"single_point_{i}_{point}"
-        tree.insert(point, point, data)
-        simple.insert(point, point, data)
-
-        assert is_balanced(
-            tree
-        ), f"Tree unbalanced after inserting single point {point}"
-
-        # Test the exact point and neighbors
-        for test_point in [point - 1, point, point + 1]:
-            if 0 <= test_point <= 100:
-                tree_result = tree.find_smallest_interval(test_point)
-                simple_result = simple.find_smallest_interval(test_point)
-                assert tree_result == simple_result
-
-
-def test_unique_intervals_override():
-    """Test that inserting an interval with the same start/end overrides the previous value."""
-    tree = IntervalTree[str]()
-
-    tree.insert(10, 20, "original_value")
-    assert tree.find_smallest_interval(15) == "original_value"
-
-    tree.insert(10, 20, "new_value")
-    assert tree.find_smallest_interval(15) == "new_value"
-
-    tree.insert(10, 25, "different_interval")
-    results = tree.search(15)
-    assert "new_value" in results
-    assert "different_interval" in results
-    assert len(results) == 2
-
-    tree.insert(10, 20, "final_value")
-    assert tree.find_smallest_interval(15) == "final_value"
-
-    assert is_balanced(tree)

tests/test_kernel_locking.py

@@ -2,17 +2,9 @@ from dataclasses import dataclass
 from pathlib import Path
 
 import pytest
-import torch.nn as nn
 
 from kernels import load_kernel
 from kernels.cli import download_kernels
-from kernels.layer import (
-    LockedLayerRepository,
-    Mode,
-    kernelize,
-    use_kernel_forward_from_hub,
-    use_kernel_mapping,
-)
 
 
 # Mock download arguments class.
@@ -27,34 +19,9 @@ def test_download_all_hash_validation():
     download_kernels(DownloadArgs(all_variants=True, project_dir=project_dir))
 
 
-@pytest.mark.cuda_only
+@pytest.mark.linux_only
 def test_load_locked():
     project_dir = Path(__file__).parent / "kernel_locking"
     # Also validates that hashing works correctly.
     download_kernels(DownloadArgs(all_variants=False, project_dir=project_dir))
     load_kernel("kernels-community/activation", lockfile=project_dir / "kernels.lock")
-
-
-def test_layer_locked():
-    project_dir = Path(__file__).parent / "layer_locking"
-
-    @use_kernel_forward_from_hub("Version")
-    class Version(nn.Module):
-        def forward(self) -> str:
-            return "0.0.0"
-
-    version = Version()
-
-    with use_kernel_mapping(
-        {
-            "Version": {
-                "cuda": LockedLayerRepository(
-                    repo_id="kernels-test/versions",
-                    layer_name="Version",
-                    lockfile=project_dir / "kernels.lock",
-                )
-            },
-        }
-    ):
-        version = kernelize(version, device="cuda", mode=Mode.INFERENCE)
-        assert version() == "0.1.1"

tests/test_kernel_upload.py

@@ -1,88 +0,0 @@
-import logging
-import os
-import re
-import tempfile
-from dataclasses import dataclass
-from pathlib import Path
-from typing import List
-
-import pytest
-from huggingface_hub import model_info
-
-from kernels.cli import upload_kernels
-
-REPO_ID = "kernels-test/kernels-upload-test"
-
-PY_CONTENT = """\
-#!/usr/bin/env python3
-
-def main():
-    print("Hello from torch-universal!")
-
-if __name__ == "__main__":
-    main()
-"""
-
-
-@dataclass
-class UploadArgs:
-    kernel_dir: None
-    repo_id: None
-    private: False
-
-
-def next_filename(path: Path) -> Path:
-    """
-    Given a path like foo_2050.py, return foo_2051.py.
-    """
-    m = re.match(r"^(.*?)(\d+)(\.py)$", path.name)
-    if not m:
-        raise ValueError(
-            f"Filename {path.name!r} does not match pattern <prefix>_<number>.py"
-        )
-
-    prefix, number, suffix = m.groups()
-    new_number = str(int(number) + 1).zfill(len(number))
-    return path.with_name(f"{prefix}{new_number}{suffix}")
-
-
-def get_filename_to_change(repo_filenames):
-    for f in repo_filenames:
-        if "foo" in f and f.endswith(".py"):
-            filename_to_change = os.path.basename(f)
-            break
-    assert filename_to_change
-    return filename_to_change
-
-
-def get_filenames_from_a_repo(repo_id: str) -> List[str]:
-    try:
-        repo_info = model_info(repo_id=repo_id, files_metadata=True)
-        repo_siblings = repo_info.siblings
-        if repo_siblings is not None:
-            return [f.rfilename for f in repo_siblings]
-        else:
-            raise ValueError("No repo siblings found.")
-    except Exception as e:
-        logging.error(f"Error connecting to the Hub: {e}.")
-
-
-@pytest.mark.token
-def test_kernel_upload_deletes_as_expected():
-    repo_filenames = get_filenames_from_a_repo(REPO_ID)
-    filename_to_change = get_filename_to_change(repo_filenames)
-
-    with tempfile.TemporaryDirectory() as tmpdir:
-        path = f"{tmpdir}/build/torch-universal/upload_test"
-        build_dir = Path(path)
-        build_dir.mkdir(parents=True, exist_ok=True)
-        changed_filename = next_filename(Path(filename_to_change))
-        script_path = build_dir / changed_filename
-        script_path.write_text(PY_CONTENT)
-        upload_kernels(UploadArgs(tmpdir, REPO_ID, False))
-
-    repo_filenames = get_filenames_from_a_repo(REPO_ID)
-    assert any(str(changed_filename) in k for k in repo_filenames), f"{repo_filenames=}"
-    assert not any(
-        str(filename_to_change) in k for k in repo_filenames
-    ), f"{repo_filenames=}"