diff --git a/.github/workflows/nightly-release.yml b/.github/workflows/nightly-release.yml
index 5bd875c5899..091c2fbada0 100644
--- a/.github/workflows/nightly-release.yml
+++ b/.github/workflows/nightly-release.yml
@@ -153,7 +153,7 @@ jobs:
       - name: Build wheel in container
         env:
           DOCKER_IMAGE: ${{ matrix.arch == 'aarch64' && format('pytorch/manylinuxaarch64-builder:cuda{0}', matrix.cuda) || format('pytorch/manylinux2_28-builder:cuda{0}', matrix.cuda) }}
-          FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '12.9' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || (matrix.cuda < '13.0' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f' || (matrix.arch == 'aarch64' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f')) }}
+          FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '12.9' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || (matrix.cuda < '13.0' && (matrix.arch == 'aarch64' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f 12.1a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f') || (matrix.arch == 'aarch64' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f 12.1a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f')) }}
           FLASHINFER_DEV_RELEASE_SUFFIX: ${{ needs.setup.outputs.dev_suffix }}
         run: |
           # Extract CUDA major and minor versions
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 38e6e0705ff..0f5586a515c 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -182,7 +182,7 @@ jobs:
       - name: Build wheel in container
         env:
           DOCKER_IMAGE: ${{ matrix.arch == 'aarch64' && format('pytorch/manylinuxaarch64-builder:cuda{0}', matrix.cuda) || format('pytorch/manylinux2_28-builder:cuda{0}', matrix.cuda) }}
-          FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '12.9' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || (matrix.cuda < '13.0' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f' || (matrix.arch == 'aarch64' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f')) }}
+          FLASHINFER_CUDA_ARCH_LIST: ${{ matrix.cuda < '12.9' && '7.5 8.0 8.9 9.0a 10.0a 12.0a' || (matrix.cuda < '13.0' && (matrix.arch == 'aarch64' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f 12.1a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f') || (matrix.arch == 'aarch64' && '7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f 12.1a' || '7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0f')) }}
         run: |
           # Extract CUDA major and minor versions
           CUDA_MAJOR=$(echo "${{ matrix.cuda }}" | cut -d'.' -f1)
diff --git a/CLAUDE.md b/CLAUDE.md
index 1f43d30da66..e295af8a674 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -585,7 +585,8 @@ When ready to distribute:
 ```bash
 # Build flashinfer-jit-cache package
 cd flashinfer-jit-cache
-export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 11.0a 12.0f"
+# The full list below needs CUDA 13.0; trim it for older toolkits.
+export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f 12.1a"
 python -m build --no-isolation --wheel
 ```
 
diff --git a/README.md b/README.md
index 3df96506797..2fc65dd69e3 100644
--- a/README.md
+++ b/README.md
@@ -166,7 +166,8 @@ python -m pip install dist/*.whl
 
 ```bash
 # flashinfer-jit-cache (customize for your target GPUs)
-export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f"
+# The full list below needs CUDA 13.0; trim it for older toolkits.
+export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f 12.1a"
 cd flashinfer-jit-cache
 python -m build --no-isolation --wheel
 python -m pip install dist/*.whl
diff --git a/docs/installation.rst b/docs/installation.rst
index d9a2098d705..43ba765edf3 100644
--- a/docs/installation.rst
+++ b/docs/installation.rst
@@ -105,11 +105,11 @@ You can follow the steps below to install FlashInfer from source code:
        python -m build --no-isolation --wheel
        python -m pip install dist/*.whl
 
-   Build ``flashinfer-jit-cache`` (customize ``FLASHINFER_CUDA_ARCH_LIST`` for your target GPUs):
+   Build ``flashinfer-jit-cache`` (customize ``FLASHINFER_CUDA_ARCH_LIST`` for your target GPUs; the full list below needs CUDA 13.0, trim it for older toolkits):
 
    .. code-block:: bash
 
-       export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f"
+       export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 11.0a 12.0f 12.1a"
        cd flashinfer-jit-cache
        python -m build --no-isolation --wheel
        python -m pip install dist/*.whl
diff --git a/scripts/task_test_jit_cache_package_build_import.sh b/scripts/task_test_jit_cache_package_build_import.sh
index 7e397ab0ad9..3c03cc04eeb 100755
--- a/scripts/task_test_jit_cache_package_build_import.sh
+++ b/scripts/task_test_jit_cache_package_build_import.sh
@@ -143,17 +143,22 @@ arches = ["7.5", "8.0", "8.9", "9.0a"]
 if cuda_ver is not None:
     try:
         major, minor = map(int, cuda_ver.split(".")[:2])
+        machine = (os.environ.get("ARCH") or platform.machine()).lower()
+        is_aarch64 = machine in ("aarch64", "arm64")
         if (major, minor) >= (13, 0):
             arches.append("10.0a")
             arches.append("10.3a")
-            machine = (os.environ.get("ARCH") or platform.machine()).lower()
-            if machine in ("aarch64", "arm64"):
+            if is_aarch64:
                 arches.append("11.0a")
             arches.append("12.0f")
+            if is_aarch64:
+                arches.append("12.1a")
         elif (major, minor) >= (12, 9):
             arches.append("10.0a")
             arches.append("10.3a")
             arches.append("12.0f")
+            if is_aarch64:
+                arches.append("12.1a")
         elif (major, minor) >= (12, 8):
             arches.append("10.0a")
             arches.append("12.0a")