jittor安装成功但调用cuda失败

问答
1

jittor安装成功但是测试cuda时提示
FAILED (failures=2)
This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.
请问有解决办法吗？

2

请您提供完整的运行输出以便查找原因

3

[w 0731 10:29:14.352000 92 compile_extern.py:200] CUDA related path found in LD_LIBRARY_PATH or PATH([‘D’, ‘\CUDA\CUDA Development\bin’, ‘D’, ‘\CUDA\CUDA Development\libnvvp’, ‘C’, ‘\Users\KyleL\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\lib64’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\mkl\dnnl_win_2.2.0_cpu_vcomp\bin’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\mkl\dnnl_win_2.2.0_cpu_vcomp\lib’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\jt1.3.4\cl\py3.9.12\Windows-10-10.x5b\AMDRyzen95900Hx49\default’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\jt1.3.4\cl\py3.9.12\Windows-10-10.x5b\AMDRyzen95900Hx49\default\cu11.2.67’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\lib\x64’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\msvc\win10_kits\lib\ucrt\x64’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\msvc\win10_kits\lib\um\x64’, ‘’, ‘C’, ‘\Users\KyleL\.cache\jittor\msvc\VC\lib’, ‘’, ‘d’, ‘\anaconda3\libs’, ‘C’, ‘\Users\KyleL\.cache\jittor\msvc\VC\\\\\_\bin’, ‘D’, ‘\Anaconda3’, ‘D’, ‘\Anaconda3\Library\mingw-w64\bin’, ‘D’, ‘\Anaconda3\Library\usr\bin’, ‘D’, ‘\Anaconda3\Library\bin’, ‘D’, ‘\Anaconda3\Scripts’, ‘D’, ‘\Anaconda3\bin’, ‘D’, ‘\Anaconda3\condabin’, ‘D’, ‘\SIMULIA\Commands’, ‘C’, ‘\Program Files\Microsoft MPI\Bin’, ‘C’, ‘\WINDOWS\system32’, ‘C’, ‘\WINDOWS’, ‘C’, ‘\WINDOWS\System32\Wbem’, ‘C’, ‘\WINDOWS\System32\WindowsPowerShell\v1.0’, ‘C’, ‘\WINDOWS\System32\OpenSSH’, ‘D’, ‘\Bandizip’, ‘D’, ‘\Matlab R2022a\runtime\win64’, ‘D’, ‘\Matlab R2022a\bin’, ‘C’, ‘\Program Files\NVIDIA Corporation\NVIDIA NvDLISR’, ‘C’, ‘\Program Files (x86)\NVIDIA Corporation\PhysX\Common’, ‘C’, ‘\Program Files\NVIDIA Corporation\Nsight Compute 2021.1.0’, ‘D’, ‘\OpenCV\opencv\build\x64\vc15\bin’, ‘D’, ‘\Anaconda3\Scripts’, ‘D’, ‘\Anaconda3\Library\bin’, ‘D’, ‘\Anaconda3\python.exe’, ‘C’, ‘\Users\KyleL\AppData\Local\Microsoft\WindowsApps’, ‘.’]), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.

4

[i 0731 20:06:54.858000 40 compiler.py:955] Jittor(1.3.4.19) src: d:\anaconda3\lib\site-packages\jittor
[i 0731 20:06:54.898000 40 compiler.py:956] cl at C:\Users\KyleL.cache\jittor\msvc\VC_____\bin\cl.exe(19.29.30133)
[i 0731 20:06:54.899000 40 compiler.py:957] cache_path: C:\Users\KyleL.cache\jittor\jt1.3.4\cl\py3.9.12\Windows-10-10.x5b\AMDRyzen95900Hx49\default
[i 0731 20:06:54.950000 40 install_cuda.py:53] cuda_driver_version: [11, 7, 0]
[i 0731 20:06:54.993000 40 __init__.py:411] Found C:\Users\KyleL.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\KyleL.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe.
[i 0731 20:06:55.021000 40 compiler.py:1010] cuda key:cu11.2.67
[i 0731 20:06:55.023000 40 __init__.py:227] Total mem: 39.41GB, using 13 procs for compiling.
[i 0731 20:06:58.200000 40 jit_compiler.cc:28] Load cc_path: C:\Users\KyleL.cache\jittor\msvc\VC_____\bin\cl.exe
[i 0731 20:06:58.213000 40 init.cc:62] Found cuda archs: [86,]
[i 0731 20:06:58.915000 40 compile_extern.py:516] mpicc not found, distribution disabled.
[i 0731 20:07:03.309000 40 cuda_flags.cc:32] CUDA enabled.
[i 0731 20:07:03.321000 40 v10 op.cc:271] Jit op key not found: curand_random?T:float32?R:uniform?JIT:1?JIT_cuda:1?index_t:int32
[i 0731 20:07:03.342000 40 v10 op.cc:278] Get jit op entry: 00007FFD6D3F1150
[i 0731 20:07:03.346000 40 v100 op.cc:267] Jit op key found: curand_random?T:float32?R:uniform?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFD6D3F1150
[i 0731 20:07:03.379000 40 v10 op.cc:271] Jit op key not found: cudnn_conv?Tx:float32?Ty:float32?Tw:float32?XFORMAT:acdb?WFORMAT:oihw?YFORMAT:acdb?JIT:1?JIT_cuda:1?index_t:int32
[i 0731 20:07:03.400000 40 v10 op.cc:278] Get jit op entry: 00007FFCDACF11A0
[i 0731 20:07:04.512000 40 cuda_flags.cc:32] CUDA enabled.
[i 0731 20:07:04.512000 40 v100 op.cc:267] Jit op key found: curand_random?T:float32?R:uniform?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFD6D3F1150
[i 0731 20:07:04.512000 40 v100 op.cc:267] Jit op key found: curand_random?T:float32?R:uniform?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFD6D3F1150
[i 0731 20:07:04.554000 40 v100 op.cc:267] Jit op key found: cudnn_conv?Tx:float32?Ty:float32?Tw:float32?XFORMAT:acdb?WFORMAT:oihw?YFORMAT:acdb?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFCDACF11A0
[i 0731 20:07:04.599000 40 cuda_flags.cc:32] CUDA enabled.
[i 0731 20:07:04.599000 40 v100 op.cc:267] Jit op key found: curand_random?T:float32?R:uniform?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFD6D3F1150
[i 0731 20:07:04.600000 40 v100 op.cc:267] Jit op key found: curand_random?T:float32?R:uniform?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFD6D3F1150
[i 0731 20:07:04.647000 40 v100 op.cc:267] Jit op key found: cudnn_conv?Tx:float32?Ty:float32?Tw:float32?XFORMAT:acdb?WFORMAT:oihw?YFORMAT:acdb?JIT:1?JIT_cuda:1?index_t:int32 jit op entry: 00007FFCDACF11A0
…[i 0731 20:07:04.688000 40 cuda_flags.cc:32] CUDA enabled.
F[i 0731 20:07:05.352000 40 cuda_flags.cc:32] CUDA enabled.
[i 0731 20:07:05.369000 40 cuda_flags.cc:32] CUDA enabled.
F

FAIL: test_conv3d (main.TestCudnnConvOp)

Traceback (most recent call last):
File “D:\Anaconda3\lib\site-packages\jittor\test\test_cudnn_op.py”, line 150, in test_conv3d
check((2,4,10,10,10), (5,4,3,3,3), (1,1,1), (1,1,1))
File “D:\Anaconda3\lib\site-packages\jittor\test\test_cudnn_op.py”, line 148, in check
np.testing.assert_allclose(dw.data, dw2.data, rtol=1e-5, atol=1e-3)
File “D:\Anaconda3\lib\site-packages\numpy\testing_private\utils.py”, line 1530, in assert_allclose
assert_array_compare(compare, actual, desired, err_msg=str(err_msg),
File “D:\Anaconda3\lib\site-packages\numpy\testing_private\utils.py”, line 844, in assert_array_compare
raise AssertionError(msg)
AssertionError:
Not equal to tolerance rtol=1e-05, atol=0.001

Mismatched elements: 516 / 540 (95.6%)
Max absolute difference: 0.1300354
Max relative difference: 0.00036617
x: array([[[[[354.5 , 388.25, 349.75],
[392.5 , 429.75, 387. ],
[348.75, 387.5 , 348.25]],…
y: array([[[[[354.51117, 388.28586, 349.81958],
[392.41412, 429.79657, 386.89883],
[348.64087, 387.39352, 348.361 ]],…

======================================================================
FAIL: test_conv_transpose3d (main.TestCudnnConvOp)

Traceback (most recent call last):
File “D:\Anaconda3\lib\site-packages\jittor\test\test_cudnn_op.py”, line 184, in test_conv_transpose3d
check((2,5,10,10,10), (5,4,3,3,3), (1,1,1), (1,1,1))
File “D:\Anaconda3\lib\site-packages\jittor\test\test_cudnn_op.py”, line 182, in check
np.testing.assert_allclose(dw.numpy(), dw2.numpy(), rtol=1e-5, atol=1e-3)
File “D:\Anaconda3\lib\site-packages\numpy\testing_private\utils.py”, line 1530, in assert_allclose
assert_array_compare(compare, actual, desired, err_msg=str(err_msg),
File “D:\Anaconda3\lib\site-packages\numpy\testing_private\utils.py”, line 844, in assert_array_compare
raise AssertionError(msg)
AssertionError:
Not equal to tolerance rtol=1e-05, atol=0.001

Mismatched elements: 525 / 540 (97.2%)
Max absolute difference: 0.1300354
Max relative difference: 0.0003474
x: array([[[[[376.25, 416. , 370. ],
[420.75, 463.5 , 408.75],
[377.75, 417.75, 366.75]],…
y: array([[[[[376.17206, 415.91016, 369.96164],
[420.66846, 463.48962, 408.76892],
[377.75873, 417.65686, 366.78934]],…

Ran 5 tests in 2.152s

FAILED (failures=2)

5

您好，请问您这个问题解决了吗，怎么解决的呀