Metadata-Version: 2.4
Name: sgl-kernel
Version: 0.3.8
Summary: Kernel Library for SGLang
License:                                  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 2023-2024 SGLang Team
        
           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.
        
Project-URL: Homepage, https://github.com/sgl-project/sglang/tree/main/sgl-kernel
Project-URL: Bug Tracker, https://github.com/sgl-project/sglang/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Environment :: GPU :: NVIDIA CUDA
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# SGL Kernel

[Kernel Library](https://github.com/sgl-project/sglang/tree/main/sgl-kernel) for SGLang

[![PyPI](https://img.shields.io/pypi/v/sgl-kernel)](https://pypi.org/project/sgl-kernel)

## Installation
For CUDA 12.1 and above:

```bash
pip3 install sgl-kernel
```

For CUDA 11.8:

```bash
pip3 install sgl-kernel -i https://docs.sglang.ai/whl/cu118
```

## Build from source

Development build:

```bash
make build
```

Note:

The `sgl-kernel` is rapidly evolving. If you experience a compilation failure, try using `make rebuild`.

### Build with [ccache](https://github.com/ccache/ccache)
```bash
# or `yum install -y ccache`.
apt-get install -y ccache
# Building with ccache is enabled when ccache is installed and CCACHE_DIR is set.
export CCACHE_DIR=/path/to/your/ccache/dir
export CCACHE_BACKEND=""
export CCACHE_KEEP_LOCAL_STORAGE="TRUE"
unset CCACHE_READONLY
python -m uv build --wheel -Cbuild-dir=build --color=always .
```

### Configuring CMake Build Options
Cmake options can be configuring by adding `-Ccmake.define.<option>=<value>` to the `uv build` flags.
For example, to enable building FP4 kernels, use:
```bash
python -m uv build --wheel -Cbuild-dir=build -Ccmake.define.SGL_KERNEL_ENABLE_FP4=1 --color=always .
```
See CMakeLists.txt for more options.

### Parallel Build

We highly recommend you build sgl-kernel with Ninja. Ninja can automatically build sgl-kernel in parallel.
And if you build the sgl-kernel with cmake, you need to add `CMAKE_BUILD_PARALLEL_LEVEL` for parallel build like:

```bash
CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) python -m uv build --wheel -Cbuild-dir=build --color=always .
```

### ⚠️ Compilation Issue with `sgl-kernel` and CUDA 12.6

When compiling `sgl-kernel` with FlashAttention on a Hopper GPU using CUDA 12.6, you may encounter a segmentation fault:

```bash
kernel/build/_deps/repo-flash-attention-src/hopper/instantiations/flash_fwd_hdimall_bf16_paged_softcap_sm90.cu -o CMakeFiles/flash_ops.dir/_deps/repo-flash-attention-src/hopper/instantiations/flash_fwd_hdimall_bf16_paged_softcap_sm90.cu.o
Segmentation fault (core dumped)
```

⚠️ **Note**: To ensure that FlashAttention compiles correctly on Hopper GPU Architecture(sm90), it is strongly [recommended](https://github.com/Dao-AILab/flash-attention/issues/1453) to use:
- nvcc version: 12.6
- ptxas version: 12.8

**1. Check Current Versions**

Before proceeding, verify your current CUDA tool versions:
```bash
nvcc --version
ptxas --version
```
**2. Update ptxas to 12.8 (if needed)**

1. Save the following script to a file (e.g., `update_ptxas.sh`).
```bash
#!/usr/bin/env bash
# Source: https://github.com/Dao-AILab/flash-attention/blob/7ff1b621112ba8b538e2fc6a316f2a6b6f22e518/hopper/setup.py#L404
set -ex

if [ -z "$1" ]; then
    echo "Usage: $0 <CUDA_VERSION>"
    exit 1
fi

CUDA_VERSION=$1

if awk "BEGIN {exit !("$CUDA_VERSION" >= 12.6 && "$CUDA_VERSION" < 12.8)}"; then
    NVCC_ARCHIVE_VERSION="12.8.93"
    NVCC_ARCHIVE_NAME="cuda_nvcc-linux-x86_64-${NVCC_ARCHIVE_VERSION}-archive"
    NVCC_ARCHIVE_TAR="${NVCC_ARCHIVE_NAME}.tar.xz"
    NVCC_ARCHIVE_URL="https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/linux-x86_64/${NVCC_ARCHIVE_TAR}"

    wget "$NVCC_ARCHIVE_URL"
    tar -xf "$NVCC_ARCHIVE_TAR"

    mkdir -p /usr/local/cuda/bin
    cp "${NVCC_ARCHIVE_NAME}/bin/ptxas" /usr/local/cuda/bin/

    # Clean up temporary files
    rm -f "${NVCC_ARCHIVE_TAR}"
    rm -rf "${NVCC_ARCHIVE_NAME}"
fi
```
2. Run the script with your CUDA version as the argument, using `sudo`:
```bash
sudo bash update_ptxas.sh 12.6
# Check the version
ptxas --version
```

# Developer Guide

## Development Environment Setup

Use Docker to set up the development environment. See [Docker setup guide](https://github.com/sgl-project/sglang/blob/main/docs/developer_guide/development_guide_using_docker.md#setup-docker-container).

Create and enter development container:
```bash
docker run -itd --shm-size 32g --gpus all -v $HOME/.cache:/root/.cache --ipc=host --name sglang_zhyncs lmsysorg/sglang:dev /bin/zsh
docker exec -it sglang_zhyncs /bin/zsh
```

## Project Structure

### Dependencies

Third-party libraries:

- [CUTLASS](https://github.com/NVIDIA/cutlass)
- [FlashInfer](https://github.com/flashinfer-ai/flashinfer)
- [DeepGEMM](https://github.com/deepseek-ai/DeepGEMM)
- [FlashAttention](https://github.com/Dao-AILab/flash-attention)

### FlashAttention FYI

  FA3 can fail without a enough shared memory for a some shapes, such as higher hidden_dim or some special cases. Right now, fa3 is supported for sm80/sm87 and sm86/sm89.

  The main different Between sm80/sm87 and sm86/sm89 is the shared memory size. you can follow the link below for more information https://docs.nvidia.com/cuda/cuda-c-programming-guide/#shared-memory-8-x.

  And for sgl-kernel right now, we can build fa3 on sm80/sm86/sm89/sm90a. That means if you use **A100(tested)**/A*0/**L20(tested)**/L40/L40s/**3090(tested)** you can use fa3.

### Kernel Development

Steps to add a new kernel:

1. Implement the kernel in [csrc](https://github.com/sgl-project/sglang/tree/main/sgl-kernel/csrc)
2. Expose the interface in [include/sgl_kernel_ops.h](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/include/sgl_kernel_ops.h)
3. Create torch extension in [csrc/common_extension.cc](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/csrc/common_extension.cc)
4. Update [CMakeLists.txt](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/CMakeLists.txt) to include new CUDA source
5. Expose Python interface in [python](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/python/sgl_kernel)

### Development Tips

1. When implementing kernels in [csrc](https://github.com/sgl-project/sglang/tree/main/sgl-kernel/csrc), only define pure CUDA files and C++ interfaces. If you need to use `Torch::tensor`, use `<torch/all.h>` instead of `<torch/extension.h>`. Using `<torch/extension.h>` will cause compilation errors when using SABI.

2. When creating torch extensions, add the function definition with `m.def`, and device binding with `m.impl`:
- Using torch.compile need `m.def` with schema, it helps auto capture the custom kernel. Reference: [How to add FakeTensor](https://docs.google.com/document/d/1_W62p8WJOQQUzPsJYa7s701JXt0qf2OfLub2sbkHOaU/edit?tab=t.0#heading=h.ptttacy8y1u9)

- How to write schema: [Schema reference](https://github.com/pytorch/pytorch/blob/main/aten/src/ATen/native/README.md#func)

   ```cpp
   // We need def with schema here for torch.compile
   m.def(
    "bmm_fp8(Tensor A, Tensor B, Tensor! D, Tensor A_scale, Tensor B_scale, Tensor workspace_buffer, int "
    "cublas_handle, int cuda_stream) -> ()");
   m.impl("bmm_fp8", torch::kCUDA, &bmm_fp8);
   ```

3. When exposing Python interfaces, avoid using kwargs in C++ interface kernels.

    **Avoid this:**

    ```cpp
    torch.ops.sgl_kernel.apply_rope_pos_ids_cos_sin_cache.default(
        q=query.view(query.shape[0], -1, head_size),
        k=key.view(key.shape[0], -1, head_size),
        q_rope=query.view(query.shape[0], -1, head_size),
        k_rope=key.view(key.shape[0], -1, head_size),
        cos_sin_cache=cos_sin_cache,
        pos_ids=positions.long(),
        interleave=(not is_neox),
        cuda_stream=get_cuda_stream(),
    )
    ```

    **Use this instead:**

    ```cpp
    torch.ops.sgl_kernel.apply_rope_pos_ids_cos_sin_cache.default(
        query.view(query.shape[0], -1, head_size),
        key.view(key.shape[0], -1, head_size),
        query.view(query.shape[0], -1, head_size),
        key.view(key.shape[0], -1, head_size),
        cos_sin_cache,
        positions.long(),
        (not is_neox),
        get_cuda_stream(),
    )
    ```

### Integrating Third-Party Libraries with Data Type Conversion

When integrating new third-party libraries like flash-attention, you may encounter data type compatibility issues between the C++ interface and PyTorch bindings. For example, the third-party code might use `float` or `int` types, while PyTorch requires `double` and `int64_t`.

> The reason we need `double` and `int64_t` in torch binding is that TORCH_LIBRARY handles the `Python-to-C++` conversion process. Python's `float` data type actually corresponds to `double` in C++, while Python's `int` corresponds to `int64_t` in C++.

To address this issue, we provide the `make_pytorch_shim` function in [sgl_kernel_torch_shim](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/include/sgl_kernel_torch_shim.h) that handles data type conversions automatically.

When you need to support new data type conversions, you can easily add conversion functions like this:

```cpp
// Map `int` -> `int64_t`
template <>
struct pytorch_library_compatible_type<int> {
  using type = int64_t;
  static int convert_from_type(int64_t arg) {
    TORCH_CHECK(arg <= std::numeric_limits<int>::max(), "int64_t value is too large to be converted  to int");
    TORCH_CHECK(arg >= std::numeric_limits<int>::min(), "int64_t value is too small to be converted to int");
    return arg;
  }
};
```

To use this with your library functions, simply wrap them with make_pytorch_shim:

```cpp
/*
 * From flash-attention
 */
 m.impl("fwd", torch::kCUDA, make_pytorch_shim(&mha_fwd));
```

### Testing & Benchmarking

1. Add pytest tests in [tests/](https://github.com/sgl-project/sglang/tree/main/sgl-kernel/tests), if you need to skip some test, please use `@pytest.mark.skipif`

```python
@pytest.mark.skipif(
    skip_condition, reason="Nvfp4 Requires compute capability of 10 or above."
)
```

2. Add benchmarks using [triton benchmark](https://triton-lang.org/main/python-api/generated/triton.testing.Benchmark.html) in [benchmark/](https://github.com/sgl-project/sglang/tree/main/sgl-kernel/benchmark)
3. Run test suite

### FAQ

- When encountering this error while compiling using ccache: `ImportError: /usr/local/lib/python3.10/dist-packages/sgl_kernel/common_ops.abi3.so: undefined symbol: _ZN3c108ListType3getERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEENS_4Type24SingletonOrSharedTypePtrIS9_EE`, please modify the last command as follows to resolve it: `python3 -m uv build --wheel -Cbuild-dir=build . --color=always --no-build-isolation` .

### Release new version

Update version in [pyproject.toml](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/pyproject.toml) and [version.py](https://github.com/sgl-project/sglang/blob/main/sgl-kernel/python/sgl_kernel/version.py)
