[CI] python: Move the remaining CUDA build paths off Python 3.10 (#44393)

Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>

.github/workflows/_pr-test-sgl-kernel-build.yml

@@ -50,7 +50,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - python-version: "3.10"
+          - python-version: "3.11"
             cuda-version: "13.0"
     name: ${{ inputs.job_display_name }}
     steps:

.github/workflows/_pr-test-stage.yml

@@ -147,7 +147,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Download artifacts (v6)
         if: ${{ fromJson(inputs.check_changes).sgl_kernel == 'true' && steps.rc.outputs.artifact_version == 'v6' }}
@@ -155,7 +155,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - uses: ./.github/actions/download-rust-ext
         if: ${{ !inputs.skip_prebuilt_rust_ext }}

.github/workflows/bot-bump-docs-version.yml

@@ -58,11 +58,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
-
-      - name: Install Python dependencies
-        run: |
-          pip install tomli
+          python-version: '3.12'
 
       - name: Configure Git and branch
         run: |

.github/workflows/bot-bump-flashinfer-version.yml

@@ -24,11 +24,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
-
-      - name: Install Python dependencies
-        run: |
-            pip install tomli
+          python-version: '3.12'
 
       - name: Configure Git and branch
         run: |

.github/workflows/bot-bump-kernel-version-to-sglang.yml

@@ -22,11 +22,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
-
-      - name: Install Python dependencies
-        run: |
-          pip install tomli
+          python-version: '3.12'
 
       - name: Check if sync is needed
         id: check_sync

.github/workflows/bot-bump-kernel-version.yml

@@ -24,11 +24,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
-
-      - name: Install Python dependencies
-        run: |
-          pip install tomli
+          python-version: '3.12'
 
       - name: Configure Git and branch
         run: |

.github/workflows/bot-bump-sglang-version.yml

@@ -26,11 +26,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
-
-      - name: Install Python dependencies
-        run: |
-          pip install tomli
+          python-version: '3.12'
 
       - name: Configure Git and branch
         id: set_output

.github/workflows/ci-coverage-overview.yml

@@ -25,7 +25,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Generate Summary Report
         run: |
@@ -41,7 +41,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Generate Tests by Folder Report
         run: |
@@ -57,7 +57,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Generate Tests by Suite Report
         run: |
@@ -73,7 +73,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Generate Tests by GPU Count Report
         run: |
@@ -184,7 +184,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Generate JSON Report
         run: |

.github/workflows/diffusion-ci-gt-gen.yml

@@ -24,7 +24,7 @@ on:
         default: ''
         type: string
       kernel_artifact_run_id:
-        description: "Optional sgl-kernel wheel source: GitHub Actions run ID of a pr-test.yml run on the SAME commit as 'ref' that uploaded wheel-python3.10-cuda13.0. Use only when this branch's torch/ABI change makes the PyPI sglang-kernel wheel incompatible. Find it under Actions > pr-test; artifacts expire after 90 days."
+        description: "Optional sgl-kernel wheel source: GitHub Actions run ID of a pr-test.yml run on the SAME commit as 'ref' that uploaded wheel-python3.11-cuda13.0. Use only when this branch's torch/ABI change makes the PyPI sglang-kernel wheel incompatible. Find it under Actions > pr-test; artifacts expire after 90 days."
         required: false
         default: ''
         type: string
@@ -204,7 +204,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          name: wheel-python3.10-cuda13.0
+          name: wheel-python3.11-cuda13.0
           run-id: ${{ inputs.kernel_artifact_run_id }}
           github-token: ${{ secrets.GITHUB_TOKEN }}
 
@@ -351,7 +351,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Verify write access to sgl-project/ci-data-diffusion
         if: ${{ inputs.publish }}
@@ -403,7 +403,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          name: wheel-python3.10-cuda13.0
+          name: wheel-python3.11-cuda13.0
           run-id: ${{ inputs.kernel_artifact_run_id }}
           github-token: ${{ secrets.GITHUB_TOKEN }}
 
@@ -479,7 +479,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          name: wheel-python3.10-cuda13.0
+          name: wheel-python3.11-cuda13.0
           run-id: ${{ inputs.kernel_artifact_run_id }}
           github-token: ${{ secrets.GITHUB_TOKEN }}
 
@@ -557,7 +557,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          name: wheel-python3.10-cuda13.0
+          name: wheel-python3.11-cuda13.0
           run-id: ${{ inputs.kernel_artifact_run_id }}
           github-token: ${{ secrets.GITHUB_TOKEN }}
 
@@ -630,7 +630,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          name: wheel-python3.10-cuda13.0
+          name: wheel-python3.11-cuda13.0
           run-id: ${{ inputs.kernel_artifact_run_id }}
           github-token: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/pr-test-jit-kernel.yml

@@ -99,7 +99,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda13.0
+          pattern: wheel-python3.11-cuda13.0
 
       - uses: ./.github/actions/download-rust-ext
         with:

.github/workflows/pr-test-multimodal-gen.yml

@@ -65,7 +65,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Compute partitions
         id: compute
@@ -101,7 +101,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -168,7 +168,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -239,7 +239,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -304,7 +304,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -374,7 +374,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -419,7 +419,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -505,7 +505,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - name: Install dependencies
         timeout-minutes: 20
@@ -548,7 +548,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Download all execution reports
         uses: actions/download-artifact@v4

.github/workflows/pr-test-sgl-kernel.yml

@@ -56,7 +56,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - uses: ./.github/actions/download-rust-ext
         with:
@@ -95,7 +95,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - uses: ./.github/actions/download-rust-ext
         with:
@@ -146,7 +146,7 @@ jobs:
         with:
           path: python/sglang/kernels/aot/dist/
           merge-multiple: true
-          pattern: wheel-python3.10-cuda*
+          pattern: wheel-python3.11-cuda*
 
       - uses: ./.github/actions/download-rust-ext
         with:
@@ -181,7 +181,7 @@ jobs:
   #       with:
   #         path: python/sglang/kernels/aot/dist/
   #         merge-multiple: true
-  #         pattern: wheel-python3.10-cuda*
+  #         pattern: wheel-python3.11-cuda*
 
   #     - name: Install dependencies
   #       run: |

.github/workflows/release-pypi-nightly.yml

@@ -161,7 +161,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.12"
 
       - name: Update wheel index
         run: |

.github/workflows/release-pypi-pr.yml

@@ -170,7 +170,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.12"
 
       - name: Update wheel index
         run: |

.github/workflows/release-pypi.yml

@@ -104,7 +104,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.12"
 
       - name: Upload to pypi
         run: |

.github/workflows/release-whl-deepep.yml

@@ -26,7 +26,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.11", "3.12", "3.13"]
         arch: [x86_64, aarch64]
         include:
           - arch: x86_64

.github/workflows/release-whl-kernel.yml

@@ -39,7 +39,7 @@ jobs:
       (github.event_name == 'push' || github.event.inputs.target == 'all' || github.event.inputs.target == 'cu130')
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
         cuda-version: ["13.0"]
         arch: [x86_64, aarch64]
         include:
@@ -174,8 +174,9 @@ jobs:
       matrix:
         python-version: ["3.10"]
         # ROCm 10.0.0 builds inside a Python 3.12 container; the wheel is still
-        # tagged cp310-abi3 (wheel.py-api in pyproject.toml), so it stays under
-        # the same python-version leg as the 7.x wheels.
+        # tagged cp310-abi3 (build_rocm.sh sets wheel.py-api to cp310 for every
+        # ROCm flavor), so it stays under the same python-version leg as the 7.x
+        # wheels.
         #
         # A dispatch that names one flavor builds only that flavor. Every extra
         # leg is another image build on the shared AMD node, and its release job

.github/workflows/runner-utilization.yml

@@ -50,7 +50,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Unit-test report logic
         # Pure-logic tests (stdlib only, no API calls) — guards the

.github/workflows/slash-command-handler.yml

@@ -92,7 +92,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Install dependencies
         run: |

.github/workflows/weekly-update-est-time.yml

@@ -21,7 +21,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
 
       - name: Update est_time values
         env:

3rdparty/amd/wheel/sgl-kernel/build_rocm.sh

@@ -56,6 +56,19 @@ if [[ "${ROCM_VERSION}" == "1000" ]]; then
   WHEEL_ROCM_VERSION="1000"
 fi
 
+# The build reuses the CUDA pyproject.toml, which requires Python 3.11 and tags
+# its wheel cp311-abi3. The ROCm 7.2.0 image and amd-sglang still run on Python
+# 3.10, so the ROCm wheels keep the Python 3.10 floor and the cp310-abi3 tag.
+sed -i \
+  -e 's/^requires-python = ">=3.11"$/requires-python = ">=3.10"/' \
+  -e 's/^wheel.py-api = "cp311"$/wheel.py-api = "cp310"/' \
+  pyproject.toml
+if ! grep -qx 'requires-python = ">=3.10"' pyproject.toml \
+  || ! grep -qx 'wheel.py-api = "cp310"' pyproject.toml; then
+  echo "ERROR: could not set the ROCm Python 3.10 / cp310 metadata in pyproject.toml." >&2
+  exit 1
+fi
+
 # Pull and run the latest image
 echo "Pulling Docker image: ${IMAGE}"
 docker pull "${IMAGE}"
@@ -86,5 +99,6 @@ ${ROCM_SETUP}
   rm -rf CMakeLists.txt && mv CMakeLists_rocm.txt CMakeLists.txt && \
   ${PYTHON_ROOT_PATH}/python rocm_hipify.py && \
   ${PYTHON_ROOT_PATH}/python -m uv build --wheel -Cbuild-dir=build . --color=always --no-build-isolation && \
-  ./rename_wheels_rocm.sh ${WHEEL_ROCM_VERSION}
+  ./rename_wheels_rocm.sh ${WHEEL_ROCM_VERSION} && \
+  ${PYTHON_ROOT_PATH}/pip install --dry-run --no-deps dist/*.whl
 "

python/pyproject.toml

@@ -30,8 +30,6 @@ dependencies = [
   "build",
   "compressed-tensors==0.18.0",
   "cuda-python>=13.0",
-  # Transitive dep of flashinfer-python, pinned because 1.6.0rc6 shipped no cp310 linux x86_64 wheel.
-  "cuda-tile==1.6.0rc5",
   "datasets",
   "decord2 ; sys_platform == 'linux' and (platform_machine == 'aarch64' or platform_machine == 'arm64' or platform_machine == 'armv7l')",
   "distro",

python/sglang/benchmark/dspark_sps_profiler.py

@@ -1,5 +1,5 @@
 # /// script
-# requires-python = ">=3.10"
+# requires-python = ">=3.11"
 # dependencies = ["msgspec", "requests", "plotly", "kaleido", "numpy"]
 # ///
 from __future__ import annotations

python/sglang/kernels/aot/Dockerfile

@@ -7,9 +7,9 @@ FROM ${BASE_IMG}:cuda${CUDA_VERSION} AS deps
 # Overridable build arguments
 ARG ARCH=x86_64
 ARG CUDA_VERSION=13.0
-ARG PYTHON_VERSION=3.10
-# Manylinux python path tag, e.g. cp310-cp310 / cp312-cp312
-ARG PYTHON_TAG=cp310-cp310
+ARG PYTHON_VERSION=3.11
+# Manylinux python path tag, e.g. cp311-cp311 / cp312-cp312
+ARG PYTHON_TAG=cp311-cp311
 ARG CMAKE_VERSION_MAJOR=3.31
 ARG CMAKE_VERSION_MINOR=1
 # Install ccache 4.12.1 from source for CUDA support (yum provides old 3.7.7)

python/sglang/kernels/aot/README.md

@@ -22,7 +22,7 @@ pip3 install sglang-kernel --upgrade
 ## Building from Source
 Requires
 - CMake ≥3.31,
-- Python ≥3.10
+- Python ≥3.11
 - scikit-build-core
 - ninja(optional)
 

python/sglang/kernels/aot/build.sh

@@ -6,7 +6,7 @@ if [ $# -lt 2 ]; then
   exit 1
 fi
 
-PYTHON_VERSION="$1"          # e.g. 3.10
+PYTHON_VERSION="$1"          # e.g. 3.11
 CUDA_VERSION="$2"            # e.g. 12.9
 ARCH="${3:-$(uname -i)}"     # optional override
 

python/sglang/kernels/aot/pyproject.toml

@@ -14,7 +14,7 @@ authors = [
 ]
 description = "Kernel Library for SGLang"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 license = { file = "LICENSE" }
 classifiers = [
   "Programming Language :: Python :: 3",
@@ -37,6 +37,6 @@ exclude = [
 cmake.build-type = "Release"
 minimum-version = "build-system.requires"
 
-wheel.py-api = "cp310"
+wheel.py-api = "cp311"
 wheel.license-files = []
 wheel.packages = ["python/sgl_kernel"]

scripts/build_sgl_deep_gemm.sh

@@ -2,7 +2,7 @@
 # Build sgl-deep-gemm wheel inside a CUDA-versioned container.
 #
 # Usage: build_sgl_deep_gemm.sh <PYTHON_VERSION> <CUDA_VERSION> <DEEPGEMM_SRC> [ARCH]
-#   PYTHON_VERSION: e.g. 3.10
+#   PYTHON_VERSION: e.g. 3.12
 #   CUDA_VERSION:   e.g. 13.0
 #   DEEPGEMM_SRC:   path to a checkout of sgl-project/DeepGEMM
 #   ARCH:           x86_64 (default) or aarch64

scripts/build_sgl_deepep.sh

@@ -13,7 +13,7 @@ usage() {
     cat <<'EOF'
 Usage: build_sgl_deepep.sh <python-version> <cuda-version> <deepep-source> [architecture]
 
-  python-version:     3.10, 3.11, 3.12, or 3.13
+  python-version:     3.11, 3.12, or 3.13
   cuda-version:       13.0
   deepep-source:      DeepEP checkout containing the sgl_deep_ep package
   architecture:       x86_64 or aarch64 (defaults to the current machine)
@@ -37,7 +37,7 @@ if [[ "${ARCHITECTURE}" == arm64 ]]; then
 fi
 
 case "${PYTHON_VERSION}" in
-    3.10|3.11|3.12|3.13) ;;
+    3.11|3.12|3.13) ;;
     *)
         echo "Unsupported Python version: ${PYTHON_VERSION}" >&2
         exit 2

scripts/ci/cuda/ci_install_dependency.sh

@@ -679,7 +679,7 @@ install_sglang_kernel() {
         else
             WHEEL_ARCH="x86_64"
         fi
-        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)
+        KERNEL_WHL=$(ls python/sglang/kernels/aot/dist/sglang_kernel-${SGL_KERNEL_VERSION_FROM_KERNEL}+${CU_VERSION}-cp311-abi3-manylinux2014_${WHEEL_ARCH}.whl 2>/dev/null | head -1 || true)
         if [ -z "$KERNEL_WHL" ]; then
             echo "ERROR: No matching sgl-kernel wheel found in 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/

scripts/release/bump_kernel_version_to_sglang.py

@@ -9,13 +9,9 @@ Updates:
 
 import re
 import sys
+import tomllib
 from pathlib import Path
 
-try:
-    import tomllib  # Python 3.11+
-except ImportError:
-    import tomli as tomllib  # Fallback for older Python versions
-
 
 def get_kernel_version_from_source() -> str:
     """Extract the version from the AOT source pyproject."""

scripts/release/check_kernel_version_to_sglang.py

@@ -10,13 +10,9 @@ Sets GitHub Actions output variables to indicate if sync is needed.
 import os
 import re
 import sys
+import tomllib
 from pathlib import Path
 
-try:
-    import tomllib  # Python 3.11+
-except ImportError:
-    import tomli as tomllib  # Fallback for older Python versions
-
 
 def get_kernel_version_from_source() -> str:
     """Extract the version from the AOT source pyproject."""

scripts/release/utils.py

@@ -1,13 +1,9 @@
 import re
 import sys
+import tomllib
 from pathlib import Path
 from typing import List, Tuple
 
-try:
-    import tomllib  # Python 3.11+
-except ImportError:
-    import tomli as tomllib  # Fallback for older Python versions
-
 
 def normalize_version(version: str) -> str:
     """Remove 'v' prefix from version string if present."""

scripts/update_kernel_whl_index.py

@@ -27,7 +27,7 @@ def check_wheel_cuda_version(path_name, target_cuda_version):
         return match.group(1) == target_cuda_version
 
     # An untagged wheel is the default-CUDA build, e.g.
-    # sglang_kernel-0.4.0-cp310-abi3-manylinux2014_x86_64.whl (PyPI rejects
+    # sglang_kernel-0.4.0-cp311-abi3-manylinux2014_x86_64.whl (PyPI rejects
     # local versions, so that upload strips the tag).
     return target_cuda_version == DEFAULT_CUDA_VERSION
 

test/registered/core/test_srt_empty_deps.py

@@ -33,11 +33,7 @@ TORCH_PULLING_PACKAGES = frozenset(
 
 def _parse_runtime_base() -> set:
     """Parse runtime_base package names from pyproject_other.toml."""
-    # Try tomllib (3.11+) or tomli
-    try:
-        import tomllib
-    except ModuleNotFoundError:
-        import tomli as tomllib  # type: ignore[no-redef]
+    import tomllib
 
     toml_path = Path(__file__).resolve().parents[3] / "python" / "pyproject_other.toml"
     if not toml_path.exists():