基于官方的mindie镜像,python推理模型运行正常,启动 mindie server正常,但是请求推理报错。
收藏回复举报
基于官方的mindie镜像,python推理模型运行正常,启动 mindie server正常,但是请求推理报错。
t('forum.solved') 已解决
新人帖
发表于2024-09-03 16:05:29
0 查看

卡信息如下:

cke_89621.png

启动信息

cke_8259.png

请求信息:

cke_14068.png

报错信息:

--- Logging error ---
--- Logging error ---
--- Logging error ---
--- Logging error ---
Traceback (most recent call last):
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 125, in __generate
    request_tokens_np, eof_np = self.__handle_requests(requests, is_prefill)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 190, in __handle_requests
    request_tokens_np, eos_np, stop_generate = self.generator.generate_token(metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 66, in generate_token
    tokens, eos_np, stop_generate = self.plugin.generate_token(input_metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/plugins/plugin.py", line 12, in generate_token
    logits = self.generator_backend.forward(model_inputs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 52, in forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 60, in forward
    logits = self.forward_tensor(
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 86, in forward_tensor
    logits = self.model_runner.forward(
  File "/usr/local/Ascend/llm_model/atb_llm/runner/model_runner.py", line 100, in forward
    return self.model.forward(**kwargs)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 229, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 200, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
RuntimeError: execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/python3.10.2/lib/python3.10/logging/__init__.py", line 1103, in emit
    stream.write(msg + self.terminator)
UnicodeEncodeError: 'ascii' codec can't encode characters in position 85-86: ordinal not in range(128)
Traceback (most recent call last):
Call stack:
Traceback (most recent call last):
Traceback (most recent call last):
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 125, in __generate
    request_tokens_np, eof_np = self.__handle_requests(requests, is_prefill)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 190, in __handle_requests
    request_tokens_np, eos_np, stop_generate = self.generator.generate_token(metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 66, in generate_token
    tokens, eos_np, stop_generate = self.plugin.generate_token(input_metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/plugins/plugin.py", line 12, in generate_token
    logits = self.generator_backend.forward(model_inputs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 52, in forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 60, in forward
    logits = self.forward_tensor(
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 86, in forward_tensor
    logits = self.model_runner.forward(
  File "/usr/local/Ascend/llm_model/atb_llm/runner/model_runner.py", line 100, in forward
    return self.model.forward(**kwargs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 125, in __generate
    request_tokens_np, eof_np = self.__handle_requests(requests, is_prefill)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 229, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 125, in __generate
    request_tokens_np, eof_np = self.__handle_requests(requests, is_prefill)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 190, in __handle_requests
    request_tokens_np, eos_np, stop_generate = self.generator.generate_token(metadata)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 200, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 190, in __handle_requests
    request_tokens_np, eos_np, stop_generate = self.generator.generate_token(metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 66, in generate_token
    tokens, eos_np, stop_generate = self.plugin.generate_token(input_metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 66, in generate_token
    tokens, eos_np, stop_generate = self.plugin.generate_token(input_metadata)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/plugins/plugin.py", line 12, in generate_token
    logits = self.generator_backend.forward(model_inputs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/plugins/plugin.py", line 12, in generate_token
    logits = self.generator_backend.forward(model_inputs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 52, in forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
RuntimeError: execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002

  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 52, in forward
    logits = self.model_wrapper.forward(model_inputs, self.cache_pool.npu_cache, **kwargs)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 60, in forward
    logits = self.forward_tensor(

During handling of the above exception, another exception occurred:

  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 60, in forward
    logits = self.forward_tensor(
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 86, in forward_tensor
    logits = self.model_runner.forward(
Traceback (most recent call last):
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 86, in forward_tensor
    logits = self.model_runner.forward(
  File "/usr/local/Ascend/llm_model/atb_llm/runner/model_runner.py", line 100, in forward
    return self.model.forward(**kwargs)
  File "/usr/local/Ascend/llm_model/atb_llm/runner/model_runner.py", line 100, in forward
    return self.model.forward(**kwargs)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 229, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 229, in forward
    logits = self.execute_ascend_operator(acl_inputs, acl_param, is_prefill)
  File "/usr/local/python3.10.2/lib/python3.10/logging/__init__.py", line 1103, in emit
    stream.write(msg + self.terminator)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 200, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
  File "/usr/local/Ascend/llm_model/atb_llm/models/base/flash_causal_lm.py", line 200, in execute_ascend_operator
    acl_model_out = self.acl_encoder_operation.execute(acl_inputs, acl_param)
UnicodeEncodeError: 'ascii' codec can't encode characters in position 85-86: ordinal not in range(128)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/model.py", line 41, in execute
    return self.python_model.execute(requests, config_map)
Call stack:
RuntimeError: execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002

RuntimeError: execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002

  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 81, in execute
    return self._prefill(requests)

During handling of the above exception, another exception occurred:


During handling of the above exception, another exception occurred:

  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 95, in _prefill
    return self.__generate(requests, is_prefill=True)
Traceback (most recent call last):
Traceback (most recent call last):
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 137, in __generate
    logger.exception(f"[Model]\t>>> Exception:{e}")
  File "/usr/local/python3.10.2/lib/python3.10/logging/__init__.py", line 1103, in emit
    stream.write(msg + self.terminator)
  File "/usr/local/python3.10.2/lib/python3.10/logging/__init__.py", line 1103, in emit
    stream.write(msg + self.terminator)
UnicodeEncodeError: 'ascii' codec can't encode characters in position 85-86: ordinal not in range(128)
UnicodeEncodeError: 'ascii' codec can't encode characters in position 85-86: ordinal not in range(128)
Message: '[Model]\t>>> Exception:execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002\n'
Arguments: ()
Call stack:
Call stack:
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/model.py", line 41, in execute
    return self.python_model.execute(requests, config_map)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 81, in execute
    return self._prefill(requests)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 95, in _prefill
    return self.__generate(requests, is_prefill=True)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 137, in __generate
    logger.exception(f"[Model]\t>>> Exception:{e}")
Message: '[Model]\t>>> Exception:execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002\n'
Arguments: ()
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/model.py", line 41, in execute
    return self.python_model.execute(requests, config_map)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/model.py", line 41, in execute
    return self.python_model.execute(requests, config_map)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 81, in execute
    return self._prefill(requests)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 81, in execute
    return self._prefill(requests)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 95, in _prefill
    return self.__generate(requests, is_prefill=True)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 95, in _prefill
    return self.__generate(requests, is_prefill=True)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 137, in __generate
    logger.exception(f"[Model]\t>>> Exception:{e}")
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 137, in __generate
    logger.exception(f"[Model]\t>>> Exception:{e}")
Message: '[Model]\t>>> Exception:execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002\n'
Arguments: ()
Message: '[Model]\t>>> Exception:execute\u5931\u8d25 \u8be6\u7ec6\u4fe1\u606f\u89c1Ascend\u5b98\u65b9\u6587\u6863\uff0c\u8bf7\u5f00\u542f\u65e5\u5fd7\u8fdb\u4e00\u6b65\u5b9a\u4f4d\u95ee\u9898\u3002\n'
Arguments: ()

模型是 chatglm2-6b,python 推理运行正常

cd /usr/local/Ascend/llm_model

# 权重转 safetensor
python examples/convert/convert_weights.py --model_path ${CHECKPOINT}

# 执行推理脚本
python examples/run_pa.py --model_path ${CHECKPOINT}

求助如何排查问题?

我要发帖子