Closed panpanli521 closed 10 months ago
图片挂了
/opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [51,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [52,0,0 layer_outputs = decoder_layer( ] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [53,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [54,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [55,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [56,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [57,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [58,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [59,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [60,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [61,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182 return forward_call(*args, **kwargs)<br> ,0,0 File "/opt/conda/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward ], thread: [62,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. /opt/conda/conda-bld/pytorch_1682343967769/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [1182,0,0], thread: [63,0,0] Assertion
index >= -sizes[i] && index < sizes[i] && "index out of bounds"failed. output = old_forward(*args, **kwargs) File "/workspace/transformers/src/transformers/models/llama/modeling_llama.py", line 633, in forward hidden_states, self_attn_weights, present_key_value = self.self_attn( File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward output = old_forward(*args, **kwargs) File "/mnt/cluster/ppl/eval_chinese/Chinese-LLaMA-Alpaca-2-main/scripts/attn_and_long_ctx_patches.py", line 58, in xformers_forward query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids) File "/workspace/transformers/src/transformers/models/llama/modeling_llama.py", line 211, in apply_rotary_pos_emb q_embed = (q * cos) + (rotate_half(q) * sin) RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with
TORCH_USE_CUDA_DSAto enable device-side assertions.
@iMountTai 麻烦看下哈
transformer回退到4.31.0试试?
transformer回退到4.31.0试试?
回退版本后,可以跑啦,多谢
提交前必须检查以下项目
问题类型
模型推理
基础模型
Chinese-LLaMA-2 (7B/13B)
操作系统
Linux
详细描述问题
依赖情况(代码类问题务必提供)
运行日志或截图