[Kernel] Move sgl-kernel under sglang.kernels.aot (#32648)

scripts/ci/amd/amd_ci_install_dependency.sh

@@ -128,7 +128,7 @@ else
   # Also clear cache in sglang-checkout
   docker exec ci_sglang find /sglang-checkout -name "*.pyc" -delete || true
   docker exec ci_sglang find /sglang-checkout -name "__pycache__" -type d -exec rm -rf {} + || true
-  docker exec -w /sglang-checkout/sgl-kernel ci_sglang bash -c "rm -f pyproject.toml && mv pyproject_rocm.toml pyproject.toml && python3 setup_rocm.py install"
+  docker exec -w /sglang-checkout/python/sglang/kernels/aot ci_sglang bash -c "rm -f pyproject.toml && mv pyproject_rocm.toml pyproject.toml && python3 setup_rocm.py install"
 
   docker exec ci_sglang bash -c 'rm -rf python/pyproject.toml && mv python/pyproject_other.toml python/pyproject.toml'
   install_with_retry docker exec ci_sglang pip install --cache-dir=/sgl-data/pip-cache -e "python[${EXTRAS}]"

scripts/ci/cuda/ci_install_dependency.sh

@@ -304,28 +304,28 @@ install_sglang() {
 }
 
 install_sglang_kernel() {
-    SGL_KERNEL_VERSION_FROM_KERNEL=$(grep -Po '(?<=^version = ")[^"]*' sgl-kernel/pyproject.toml)
+    SGL_KERNEL_VERSION_FROM_KERNEL=$(grep -Po '(?<=^version = ")[^"]*' python/sglang/kernels/aot/pyproject.toml)
     SGL_KERNEL_VERSION_FROM_SRT=$(grep -Po -m1 '(?<=sglang-kernel==)[0-9A-Za-z\.\-]+' python/pyproject.toml)
     echo "SGL_KERNEL_VERSION_FROM_KERNEL=${SGL_KERNEL_VERSION_FROM_KERNEL} SGL_KERNEL_VERSION_FROM_SRT=${SGL_KERNEL_VERSION_FROM_SRT}"
 
-    if [ "${CUSTOM_BUILD_SGL_KERNEL:-}" = "true" ] && [ -d "sgl-kernel/dist" ]; then
-        ls -alh sgl-kernel/dist
+    if [ "${CUSTOM_BUILD_SGL_KERNEL:-}" = "true" ] && [ -d "python/sglang/kernels/aot/dist" ]; then
+        ls -alh python/sglang/kernels/aot/dist
         if [ "$ARCH" = "aarch64" ] || [ "$ARCH" = "arm64" ]; then
             WHEEL_ARCH="aarch64"
         else
             WHEEL_ARCH="x86_64"
         fi
-        KERNEL_WHL=$(ls sgl-kernel/dist/sglang_kernel-${SGL_KERNEL_VERSION_FROM_KERNEL}+${CU_VERSION}-cp310-abi3-manylinux2014_${WHEEL_ARCH}.whl 2>/dev/null | head -1 || true)
+        KERNEL_WHL=$(ls python/sglang/kernels/aot/dist/sglang_kernel-${SGL_KERNEL_VERSION_FROM_KERNEL}+${CU_VERSION}-cp310-abi3-manylinux2014_${WHEEL_ARCH}.whl 2>/dev/null | head -1 || true)
         if [ -z "$KERNEL_WHL" ]; then
-            echo "ERROR: No matching sgl-kernel wheel found in sgl-kernel/dist/ for version ${SGL_KERNEL_VERSION_FROM_KERNEL} arch ${WHEEL_ARCH} cuda ${CU_VERSION}"
-            ls -alh sgl-kernel/dist/
+            echo "ERROR: No matching sgl-kernel wheel found in python/sglang/kernels/aot/dist/ for version ${SGL_KERNEL_VERSION_FROM_KERNEL} arch ${WHEEL_ARCH} cuda ${CU_VERSION}"
+            ls -alh python/sglang/kernels/aot/dist/
             exit 1
         fi
         echo "Installing sgl-kernel wheel: $KERNEL_WHL"
         $PIP_CMD install "$KERNEL_WHL" --force-reinstall $PIP_INSTALL_SUFFIX
     else
-        if [ "${CUSTOM_BUILD_SGL_KERNEL:-}" = "true" ] && [ ! -d "sgl-kernel/dist" ]; then
-            echo "ERROR: CUSTOM_BUILD_SGL_KERNEL=true but sgl-kernel/dist not found."
+        if [ "${CUSTOM_BUILD_SGL_KERNEL:-}" = "true" ] && [ ! -d "python/sglang/kernels/aot/dist" ]; then
+            echo "ERROR: CUSTOM_BUILD_SGL_KERNEL=true but python/sglang/kernels/aot/dist not found."
             echo "This usually happens when rerunning a stage without the sgl-kernel-build-wheels job."
             echo "Please re-run the full workflow using /tag-and-rerun-ci to rebuild the kernel."
             exit 1

scripts/ci/musa/musa_install_dependency.sh

@@ -84,7 +84,7 @@ else
 
     cd "${REPO_ROOT}" && ${PIP_INSTALL} -v -e "python[dev_musa]" --user
 
-    cd "${REPO_ROOT}/sgl-kernel"
+    cd "${REPO_ROOT}/python/sglang/kernels/aot"
     rm -f pyproject.toml && mv pyproject_musa.toml pyproject.toml && MTGPU_TARGET=mp_31 python3 setup_musa.py install --user
     echo "$HOME/.local/bin" >> "$GITHUB_PATH"
 fi

scripts/ci/musa/rename_wheels_musa.sh

@@ -10,7 +10,7 @@
 # Usage:
 #   rename_wheels_musa.sh <musa_suffix> [wheel_dir]
 # Example:
-#   rename_wheels_musa.sh 43 sgl-kernel/dist
+#   rename_wheels_musa.sh 43 python/sglang/kernels/aot/dist
 set -euxo pipefail
 
 if [[ $# -lt 1 || $# -gt 2 ]]; then

scripts/ci/npu/npu_log_print.sh

@@ -8,7 +8,7 @@ get_version() {
     [ -f "$1" ] && python3 -c 'import re, sys; print(sys.argv[2] + " version: v" + re.search(r"__version__\s*=\s*[\"'"'"'](.*?)[\"'"'"']", open(sys.argv[1]).read()).group(1))' "$1" "$2" 2>/dev/null || echo "$2 version: unknown"
 }
 get_version "./python/sglang/version.py" "sglang"
-get_version "./sgl-kernel/python/sgl_kernel/version.py" "sgl_kernel"
+get_version "./python/sglang/kernels/aot/python/sgl_kernel/version.py" "sgl_kernel"
 SGLANG_URL="https://github.com/sgl-project/sglang.git"
 SGL_KERNEL_URL="https://github.com/sgl-project/sgl-kernel-npu.git"
 SGLANG_BRANCH="main"

scripts/ci/utils/slash_command_handler.py

@@ -289,14 +289,14 @@ def load_permissions(user_login):
 
 def has_sgl_kernel_changes(pr):
     """
-    Check if the PR has changes to the sgl-kernel directory.
+    Check if the PR has changes to the AOT kernel directory.
     This is used to determine if we need a full workflow rerun
     (to rebuild the kernel) vs just rerunning failed jobs.
     """
     try:
         files = pr.get_files()
         for f in files:
-            if f.filename.startswith("sgl-kernel/"):
+            if f.filename.startswith("python/sglang/kernels/aot/"):
                 return True
         return False
     except Exception as e:

scripts/ci_monitor/ci_auto_bisect.py

@@ -576,7 +576,7 @@ def _infer_related_paths(test_file: str) -> List[str]:
         "specul": ["python/sglang/srt/speculative/"],
         "vision": ["python/sglang/srt/models/"],
         "embed": ["python/sglang/srt/layers/"],
-        "kernel": ["sgl-kernel/", "python/sglang/srt/layers/"],
+        "kernel": ["python/sglang/kernels/aot/", "python/sglang/srt/layers/"],
         "bench": ["benchmark/"],
         "constrained": ["python/sglang/srt/constrained/"],
     }

scripts/release/README.md

@@ -109,11 +109,11 @@ python scripts/release/bump_kernel_version.py 0.4.0
 ```
 
 **Files updated:**
-- `sgl-kernel/pyproject.toml`
-- `sgl-kernel/pyproject_cpu.toml`
-- `sgl-kernel/pyproject_rocm.toml`
-- `sgl-kernel/pyproject_musa.toml`
-- `sgl-kernel/python/sgl_kernel/version.py`
+- `python/sglang/kernels/aot/pyproject.toml`
+- `python/sglang/kernels/aot/pyproject_cpu.toml`
+- `python/sglang/kernels/aot/pyproject_rocm.toml`
+- `python/sglang/kernels/aot/pyproject_musa.toml`
+- `python/sglang/kernels/aot/python/sgl_kernel/version.py`
 
 ## Manual Testing Instructions
 
@@ -155,8 +155,8 @@ python scripts/release/bump_kernel_version.py 0.4.0
 
 3. **Check specific files contain the new version:**
    ```bash
-   grep -r "0.4.0" sgl-kernel/python/sgl_kernel/version.py
-   grep -r "0.4.0" sgl-kernel/pyproject.toml
+   grep -r "0.4.0" python/sglang/kernels/aot/python/sgl_kernel/version.py
+   grep -r "0.4.0" python/sglang/kernels/aot/pyproject.toml
    ```
 
 4. **Reset changes (if testing):**

scripts/release/bump_kernel_version.py

@@ -16,14 +16,14 @@ def main():
     )
     args = parser.parse_args()
 
-    version_file = Path("sgl-kernel/python/sgl_kernel/version.py")
+    version_file = Path("python/sglang/kernels/aot/python/sgl_kernel/version.py")
 
     files_to_update = [
-        Path("sgl-kernel/pyproject.toml"),
-        Path("sgl-kernel/pyproject_cpu.toml"),
-        Path("sgl-kernel/pyproject_rocm.toml"),
-        Path("sgl-kernel/pyproject_musa.toml"),
-        Path("sgl-kernel/python/sgl_kernel/version.py"),
+        Path("python/sglang/kernels/aot/pyproject.toml"),
+        Path("python/sglang/kernels/aot/pyproject_cpu.toml"),
+        Path("python/sglang/kernels/aot/pyproject_rocm.toml"),
+        Path("python/sglang/kernels/aot/pyproject_musa.toml"),
+        Path("python/sglang/kernels/aot/python/sgl_kernel/version.py"),
     ]
 
     bump_version(args.new_version, version_file, files_to_update)

scripts/release/bump_kernel_version_to_sglang.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Bump sglang-kernel version in SGLang files to match the version in sgl-kernel/pyproject.toml.
+Bump SGLang's kernel dependencies to match the AOT source pyproject.
 Updates:
   - python/pyproject.toml
   - python/sglang/srt/entrypoints/engine.py
@@ -18,8 +18,8 @@ except ImportError:
 
 
 def get_kernel_version_from_source() -> str:
-    """Extract version from sgl-kernel/pyproject.toml"""
-    pyproject_path = Path("sgl-kernel/pyproject.toml")
+    """Extract the version from the AOT source pyproject."""
+    pyproject_path = Path("python/sglang/kernels/aot/pyproject.toml")
 
     if not pyproject_path.exists():
         print(f"Error: {pyproject_path} not found")
@@ -30,7 +30,9 @@ def get_kernel_version_from_source() -> str:
 
     version = data.get("project", {}).get("version")
     if not version:
-        print("Error: Could not find version in sgl-kernel/pyproject.toml")
+        print(
+            "Error: Could not find version in python/sglang/kernels/aot/pyproject.toml"
+        )
         sys.exit(1)
 
     return version

scripts/release/check_kernel_version_to_sglang.py

@@ -1,7 +1,9 @@
 #!/usr/bin/env python3
 """
-Check if sglang-kernel version from sgl-kernel/pyproject.toml matches the versions
-used in SGLang files (python/pyproject.toml, engine.py, and Dockerfile).
+Check whether SGLang's kernel dependencies match the AOT source pyproject.
+
+The dependent versions are read from python/pyproject.toml, engine.py, and
+Dockerfile.
 Sets GitHub Actions output variables to indicate if sync is needed.
 """
 
@@ -17,8 +19,8 @@ except ImportError:
 
 
 def get_kernel_version_from_source() -> str:
-    """Extract version from sgl-kernel/pyproject.toml (line 11)"""
-    pyproject_path = Path("sgl-kernel/pyproject.toml")
+    """Extract the version from the AOT source pyproject."""
+    pyproject_path = Path("python/sglang/kernels/aot/pyproject.toml")
 
     if not pyproject_path.exists():
         print(f"Error: {pyproject_path} not found")
@@ -29,7 +31,9 @@ def get_kernel_version_from_source() -> str:
 
     version = data.get("project", {}).get("version")
     if not version:
-        print("Error: Could not find version in sgl-kernel/pyproject.toml")
+        print(
+            "Error: Could not find version in python/sglang/kernels/aot/pyproject.toml"
+        )
         sys.exit(1)
 
     return version
@@ -101,7 +105,9 @@ def main():
     engine_version = get_kernel_version_from_engine()
     dockerfile_version = get_kernel_version_from_dockerfile()
 
-    print(f"Kernel version in sgl-kernel/pyproject.toml: {kernel_version}")
+    print(
+        f"Kernel version in python/sglang/kernels/aot/pyproject.toml: {kernel_version}"
+    )
     print(
         f"SGLang kernel dependency version in python/pyproject.toml: {pyproject_version}"
     )

scripts/release/commit_and_pr_kernel_to_sglang.sh

@@ -28,7 +28,7 @@ git add -A
 git commit -m "chore: bump sglang-kernel version to ${KERNEL_VERSION} in SGLang
 
 This commit updates the sglang-kernel version across SGLang files to match
-the version defined in sgl-kernel/pyproject.toml.
+the version defined in python/sglang/kernels/aot/pyproject.toml.
 
 Files updated:
 ${COMMIT_FILES}
@@ -45,7 +45,7 @@ PR_URL=$(gh pr create \
   --title "chore: bump sglang-kernel version to ${KERNEL_VERSION}" \
   --body "## Summary
 
-This PR bumps the \`sglang-kernel\` version to \`${KERNEL_VERSION}\` across SGLang files to match the version defined in \`sgl-kernel/pyproject.toml\`.
+This PR bumps the \`sglang-kernel\` version to \`${KERNEL_VERSION}\` across SGLang files to match the version defined in \`python/sglang/kernels/aot/pyproject.toml\`.
 
 **Kernel Version:** \`${KERNEL_VERSION}\`
 
@@ -54,7 +54,7 @@ ${FILES_LIST}
 
 ## Context
 
-The kernel version in \`sgl-kernel/pyproject.toml\` has been updated. This PR ensures that all SGLang files referencing the \`sglang-kernel\` dependency are updated accordingly:
+The kernel version in \`python/sglang/kernels/aot/pyproject.toml\` has been updated. This PR ensures that all SGLang files referencing the \`sglang-kernel\` dependency are updated accordingly:
 - \`python/pyproject.toml\` - dependency specification
 - \`python/sglang/srt/entrypoints/engine.py\` - version check
 - \`docker/Dockerfile\` - Docker build argument

scripts/update_kernel_whl_index.py

@@ -34,7 +34,7 @@ def update_wheel_index(cuda_version=DEFAULT_CUDA_VERSION, rocm_version=None):
     index_dir.mkdir(exist_ok=True, parents=True)
     base_url = "https://github.com/sgl-project/whl/releases/download"
 
-    for path in sorted(pathlib.Path("sgl-kernel/dist").glob("*.whl")):
+    for path in sorted(pathlib.Path("python/sglang/kernels/aot/dist").glob("*.whl")):
         # Skip the wheel if mismatches the passed in cuda_version
         if not check_wheel_cuda_version(path.name, cuda_version):
             continue
@@ -53,7 +53,7 @@ def _update_non_cuda_wheel_index(backend, version):
     index_dir.mkdir(exist_ok=True, parents=True)
     base_url = "https://github.com/sgl-project/whl/releases/download"
 
-    for path in sorted(pathlib.Path("sgl-kernel/dist").glob("*.whl")):
+    for path in sorted(pathlib.Path("python/sglang/kernels/aot/dist").glob("*.whl")):
         # Skip the wheel if not for this backend
         if re.search(f"{backend}", path.name) is None:
             continue