runtime error

Exit code: 1. Reason: sitory --- 🚀 Running command: git clone https://github.com/thu-ml/SageAttention.git ✅ Repository cloned successfully. --- [SageAttention Build] Step 2/3: Patching setup.py --- --- [SageAttention Build] Applying patches to SageAttention/setup.py --- 🔧 Patch 1/1: Removed '-fopenmp' and '-lgomp' from CXX_FLAGS. ✅ Patches applied successfully. --- [SageAttention Build] Step 3/3: Compiling and installing --- 🔧 Setting build environment variables: - TORCH_CUDA_ARCH_LIST='9.0' - EXT_PARALLEL=4 - NVCC_APPEND_FLAGS='--threads 8' - MAX_JOBS=32 🚀 Running command: /usr/local/bin/python setup.py install /usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py:1007: UserWarning: Can't initialize NVML raw_cnt = _raw_device_count_nvml() W0512 18:44:04.205000 245 site-packages/torch/utils/cpp_extension.py:118] No CUDA runtime is found, using CUDA_HOME='/cuda-image/usr/local/cuda-12.9' Traceback (most recent call last): File "/home/user/app/SageAttention/setup.py", line 121, in <module> nvcc_cuda_version = get_nvcc_cuda_version(CUDA_HOME) File "/home/user/app/SageAttention/setup.py", line 84, in get_nvcc_cuda_version nvcc_output = subprocess.check_output([cuda_dir + "/bin/nvcc", "-V"], File "/usr/local/lib/python3.10/subprocess.py", line 421, in check_output return run(*popenargs, stdout=PIPE, timeout=timeout, check=True, File "/usr/local/lib/python3.10/subprocess.py", line 503, in run with Popen(*popenargs, **kwargs) as process: File "/usr/local/lib/python3.10/subprocess.py", line 971, in __init__ self._execute_child(args, executable, preexec_fn, close_fds, File "/usr/local/lib/python3.10/subprocess.py", line 1863, in _execute_child raise child_exception_type(errno_num, err_msg, err_filename) FileNotFoundError: [Errno 2] No such file or directory: '/cuda-image/usr/local/cuda-12.9/bin/nvcc' ❌ Command failed with return code: 1 ❌ Command: /usr/local/bin/python setup.py install ❌ SageAttention installation failed. Please check the logs above for details.

Container logs: