Traceback (most recent call last):
File “I:\JittorLLMs\cli_demo.py”, line 9, in
model.chat()
File “I:\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\wwj93/.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\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py”, line 1336, in stream_generate
outputs = self(
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py”, line 16, in call
return self.forward(*args, **kw)
File “C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py”, line 1138, in forward
transformer_outputs = self.transformer(
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py”, line 16, in call
return self.forward(*args, **kw)
File “C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py”, line 973, in forward
layer_ret = layer(
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py”, line 16, in call
return self.forward(*args, **kw)
File “C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py”, line 614, in forward
attention_outputs = self.attention(
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py”, line 16, in call
return self.forward(*args, **kw)
File “C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py”, line 454, in forward
cos, sin = self.rotary_emb(q1, seq_len=position_ids.max() + 1)
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py”, line 16, in call
return self.forward(*args, **kw)
File “C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py”, line 202, in forward
t = torch.arange(seq_len, device=x.device, dtype=self.inv_freq.dtype)
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch_init_.py”, line 31, in inner
ret = func(*args, **kw)
File “C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jittor\misc.py”, line 809, in arange
if isinstance(start, jt.Var): start = start.item()
RuntimeError: [f 0429 10:50:09.659000 00 executor.cc:682]
Execute fused operator(18/43) failed.
[JIT Source]: I:\JittorLLMs\cache.cache\jittor\jt1.3.7\cl\py3.9.16\Windows-10-10.x0e\IntelRCoreTMi7x56\default\cu11.2.67\jit_opkey0_broadcast_to__Tx_float16__DIM_3__BCAST_1__opkey1_broadcast_to__Tx_float16__DIM_3____hash_9730a00665a5a466_op.cc
[OP TYPE]: fused_op:( broadcast_to, broadcast_to, binary.multiply, reduce.add,)
[Input]: float16[16384,4096,]transformer.layers.9.mlp.dense_h_to_4h.weight, float16[4,4096,],
[Output]: float16[4,16384,],
[Async Backtrace]: —
I:\JittorLLMs\cli_demo.py:9 <>
I:\JittorLLMs\models\chatglm_init.py:36
C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1259 <stream_chat>
C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1336 <stream_generate>
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py:16 <call>
C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:1138
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py:16 <call>
C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:973
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py:16 <call>
C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:635
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch\nn_init_.py:16 <call>
C:\Users\wwj93/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py:535
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jtorch_init_.py:126 <call>
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jittor\nn.py:638
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jittor\nn.py:34 <matmul_transpose>
C:\Users\wwj93\Anaconda3\envs\jittor\lib\site-packages\jittor\nn.py:42 <matmul_transpose>
[Reason]: [f 0429 10:50:09.347000 00 helper_cuda.h:128] CUDA error at c:\users\wwj93\anaconda3\envs\jittor\lib\site-packages\jittor\src\mem\allocator\cuda_device_allocator.cc:33 code=2( cudaErrorMemoryAllocation ) cudaMallocManaged(&ptr, size)