fix cu118 link issue

[zhyncs]

Motivation

@BBuf @ispobock

Modifications

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.

[zhyncs]

root@9b9d06365bda:/# ldd -r /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/_kernels.abi3.so
	linux-vdso.so.1 (0x00007ffdc15a6000)
	libc10.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libc10.so (0x00007fbde80d7000)
	libtorch.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libtorch.so (0x00007fbde80b1000)
	libtorch_python.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libtorch_python.so (0x00007fbde6b3d000)
	libcuda.so.1 => /lib/x86_64-linux-gnu/libcuda.so.1 (0x00007fbde4f6a000)
	libcublas.so.11 => /usr/local/cuda/targets/x86_64-linux/lib/libcublas.so.11 (0x00007fbddf30c000)
	libtorch_cpu.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libtorch_cpu.so (0x00007fbdca24e000)
	libcudart.so.11.0 => /usr/local/cuda/targets/x86_64-linux/lib/libcudart.so.11.0 (0x00007fbdc9fa7000)
	libc10_cuda.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libc10_cuda.so (0x00007fbdc9ef1000)
	libtorch_cuda.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libtorch_cuda.so (0x00007fbd8ffe2000)
	libstdc++.so.6 => /lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007fbd8fe00000)
	libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fbd8fcb1000)
	libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007fbd8fc94000)
	libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fbd8fc71000)
	libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fbd8fa7f000)
	libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fbd8fa77000)
	/lib64/ld-linux-x86-64.so.2 (0x00007fbde929f000)
	libshm.so => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libshm.so (0x00007fbd8fa6b000)
	libcudnn.so.9 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/../../nvidia/cudnn/lib/libcudnn.so.9 (0x00007fbd8f851000)
	librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fbd8f847000)
	libcublasLt.so.11 => /usr/local/cuda/targets/x86_64-linux/lib/libcublasLt.so.11 (0x00007fbd6b2bf000)
	libgomp-a34b3233.so.1 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libgomp-a34b3233.so.1 (0x00007fbd6b095000)
	libcupti.so.11.8 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/../../nvidia/cuda_cupti/lib/libcupti.so.11.8 (0x00007fbd6a780000)
	libcusparse.so.11 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/../../nvidia/cusparse/lib/libcusparse.so.11 (0x00007fbd59a88000)
	libcufft.so.10 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/../../nvidia/cufft/lib/libcufft.so.10 (0x00007fbd48bab000)
	libcusparseLt-f8b4a9fb.so.0 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/libcusparseLt-f8b4a9fb.so.0 (0x00007fbd4686f000)
	libcurand.so.10 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/../../nvidia/curand/lib/libcurand.so.10 (0x00007fbd3ff93000)
	libnccl.so.2 => /usr/local/lib/python3.10/dist-packages/sgl_kernel/ops/../../torch/lib/../../nvidia/nccl/lib/libnccl.so.2 (0x00007fbd34fae000)
	libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007fbd34fa7000)