[i 0811 00:10:33.421000 84 compiler.py:956] Jittor(1.3.8.5) src: c:\users\huang\.conda\envs\lanmode\lib\site-packages\jittor
[i 0811 00:10:33.516000 84 compiler.py:957] cl at C:\Users\huang\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133)
[i 0811 00:10:33.516000 84 compiler.py:958] cache_path: C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default
[i 0811 00:10:33.525000 84 install_cuda.py:93] cuda_driver_version: [11, 7, 0]
[i 0811 00:10:33.652000 84 __init__.py:411] Found C:\Users\huang\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\huang\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe.
[i 0811 00:10:33.864000 84 compiler.py:1011] cuda key:cu11.2.67
[i 0811 00:10:33.866000 84 __init__.py:227] Total mem: 15.85GB, using 5 procs for compiling.
[i 0811 00:10:35.296000 84 jit_compiler.cc:28] Load cc_path: C:\Users\huang\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe
[i 0811 00:10:35.296000 84 swap.cc:29] Load cpu_mem_limit: 3000000000
[i 0811 00:10:35.296000 84 swap.cc:30] Load device_mem_limit: 3000000000
[i 0811 00:10:35.309000 84 py_var_tracer.cc:22] Load trace_py_var: 3
[i 0811 00:10:35.310000 84 init.cc:62] Found cuda archs: [61,]
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [01:12<00:00, 9.01s/it]
[i 0811 00:11:50.988000 84 cuda_flags.cc:49] CUDA enabled.
用户输入:1
[e 0811 00:12:11.924000 84 log.cc:565] cl : Command line warning D9025 : overriding '/EHa' with '/EHs'
__opkey0_array__T_int32__opkey1_broadcast_to__Tx_int32__DIM_2__BCAST_3__opkey2_binary__Tx____hash_aeb4a6050faf923f_op.cc
c:/users/huang/.conda/envs/lanmode/lib/site-packages/jittor/src\misc/cuda_atomic.h(138): error: no instance of overloaded function "atomicCAS" matches the argument list
argument types are: (unsigned short *, unsigned short, unsigned short)
c:/users/huang/.conda/envs/lanmode/lib/site-packages/jittor/src\misc/cuda_atomic.h(153): error: no instance of overloaded function "atomicCAS" matches the argument list
argument types are: (unsigned short *, unsigned short, unsigned short)
2 errors detected in the compilation of "C:/Users/huang/.cache/jittor/jt1.3.8/cl/py3.8.17/Windows-10-10.xac/12thGenIntelRCx4a/default/cu11.2.67/jit/__opkey0_array__T_int32__opkey1_broadcast_to__Tx_int32__DIM_2__BCAST_3__opkey2_binary__Tx____hash_aeb4a6050faf923f_op.cc".
__opkey0_array__T_int32__opkey1_broadcast_to__Tx_int32__DIM_2__BCAST_3__opkey2_binary__Tx____hash_aeb4a6050faf923f_op.cc
Traceback (most recent call last):
File "cli_demo.py", line 9, in <module>
model.chat()
File "C:\Users\huang\Desktop\langmode\JittorLLMs\models\chatglm\__init__.py", line 36, in chat
for response, history in self.model.stream_chat(self.tokenizer, text, history=history):
File "C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1259, in stream_chat
for outputs in self.stream_generate(**input_ids, **gen_kwargs):
File "C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1334, in stream_generate
model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
File "C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 1083, in prepare_inputs_for_generation
mask_token = MASK if MASK in input_ids else gMASK
File "C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\misc.py", line 132, in __contains__
return bool((x == key).any())
File "C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\__init__.py", line 2026, in to_bool
return ori_bool(v.item())
RuntimeError: Wrong inputs arguments, Please refer to examples(help(jt.item)).
Types of your inputs are:
self = Var,
args = (),
The function declarations are:
ItemData item()
Failed reason:[f 0811 00:12:11.929000 84 parallel_compiler.cc:331] Error happend during compilation:
[Error] source file location:C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default\cu11.2.67\jit\__opkey0_array__T_int32__opkey1_broadcast_to__Tx_int32__DIM_2__BCAST_3__opkey2_binary__Tx____hash_aeb4a6050faf923f_op.cc
Compile fused operator(1/3)failed:[Op(11766:0:1:1:i0:o1:s0,array->11767){cli_demo.py:9(<module>) ->
C:\Users\huang\Desktop\langmode\JittorLLMs\models\chatglm\__init__.py:36(chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1259(stream_chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1334(stream_generate) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1083(prepare_inputs_for_generation) ->
C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\misc.py:132(__contains__) ->
},Op(11770:0:1:1:i1:o1:s0,broadcast_to->11771){cli_demo.py:9(<module>) ->
C:\Users\huang\Desktop\langmode\JittorLLMs\models\chatglm\__init__.py:36(chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1259(stream_chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1334(stream_generate) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1083(prepare_inputs_for_generation) ->
C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\misc.py:132(__contains__) ->
},Op(11772:0:1:1:i2:o1:s0,binary.equal->11773){cli_demo.py:9(<module>) ->
C:\Users\huang\Desktop\langmode\JittorLLMs\models\chatglm\__init__.py:36(chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1259(stream_chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1334(stream_generate) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1083(prepare_inputs_for_generation) ->
C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\misc.py:132(__contains__) ->
},Op(11774:0:1:1:i1:o1:s0,reduce.logical_or->11775){cli_demo.py:9(<module>) ->
C:\Users\huang\Desktop\langmode\JittorLLMs\models\chatglm\__init__.py:36(chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1259(stream_chat) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1334(stream_generate) ->
C:\Users\huang/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1083(prepare_inputs_for_generation) ->
C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\misc.py:132(__contains__) ->
C:\Users\huang\.conda\envs\lanmode\lib\site-packages\jittor\misc.py:155(any) ->
},]
Reason: [f 0811 00:12:11.924000 84 log.cc:608] Check failed ret(1) == 0(0) Run cmd failed: "C:\Users\huang\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe" "C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default\cu11.2.67\jit\__opkey0_array__T_int32__opkey1_broadcast_to__Tx_int32__DIM_2__BCAST_3__opkey2_binary__Tx____hash_aeb4a6050faf923f_op.cc" -shared -L"c:\users\huang\.conda\envs\lanmode\libs" -lpython38 -Xcompiler -EHa -Xcompiler -MD -Xcompiler -utf-8 -I"C:\Users\huang\.cache\jittor\msvc\VC\include" -I"C:\Users\huang\.cache\jittor\msvc\win10_kits\include\ucrt" -I"C:\Users\huang\.cache\jittor\msvc\win10_kits\include\shared" -I"C:\Users\huang\.cache\jittor\msvc\win10_kits\include\um" -DNOMINMAX -L"C:\Users\huang\.cache\jittor\msvc\VC\lib" -L"C:\Users\huang\.cache\jittor\msvc\win10_kits\lib\um\x64" -L"C:\Users\huang\.cache\jittor\msvc\win10_kits\lib\ucrt\x64" -I"c:\users\huang\.conda\envs\lanmode\lib\site-packages\jittor\src" -I"c:\users\huang\.conda\envs\lanmode\include" -DHAS_CUDA -DIS_CUDA -I"C:\Users\huang\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\include" -I"c:\users\huang\.conda\envs\lanmode\lib\site-packages\jittor\extern\cuda\inc" -lcudart -L"C:\Users\huang\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\lib\x64" -L"C:\Users\huang\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin" -I"C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default\cu11.2.67" -L"C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default\cu11.2.67" -L"C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default" -l"jit_utils_core.cp38-win_amd64" -l"jittor_core.cp38-win_amd64" -x cu --cudart=shared -ccbin="C:\Users\huang\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe" --use_fast_math -w -I"c:\users\huang\.conda\envs\lanmode\lib\site-packages\jittor\extern/cuda/inc" -arch=compute_61 -code=sm_61 -o "C:\Users\huang\.cache\jittor\jt1.3.8\cl\py3.8.17\Windows-10-10.xac\12thGenIntelRCx4a\default\cu11.2.67\jit\__opkey0_array__T_int32__opkey1_broadcast_to__Tx_int32__DIM_2__BCAST_3__opkey2_binary__Tx____hash_aeb4a6050faf923f_op.dll" -Xlinker -EXPORT:"?jit_run@FusedOp@jittor@@QEAAXXZ"
1 个赞