Have error when building engines from the checkpoint
Hi, I have error when building engines.
Seems like it's caused by the weight safetensors are not named with rank0.safetensors. How should I work around this problem? Thank you very much!
[TensorRT-LLM] TensorRT-LLM version: 0.17.0.dev2024121700
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "/usr/lib/python3.12/concurrent/futures/process.py", line 263, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/usr/local/lib/python3.12/dist-packages/tensorrt_llm/commands/build.py", line 390, in build_and_save
engine = build_model(build_config,
File "/usr/local/lib/python3.12/dist-packages/tensorrt_llm/commands/build.py", line 360, in build_model
model = model_cls.from_checkpoint(ckpt_dir, config=rank_config)
File "/usr/local/lib/python3.12/dist-packages/tensorrt_llm/models/modeling_utils.py", line 642, in from_checkpoint
assert os.path.isfile(weights_path)
AssertionError
"""
I have same error.
[TensorRT-LLM] TensorRT-LLM version: 0.16.0
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/process.py", line 246, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 390, in build_and_save
engine = build_model(build_config,
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 360, in build_model
model = model_cls.from_checkpoint(ckpt_dir, config=rank_config)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/models/modeling_utils.py", line 642, in from_checkpoint
assert os.path.isfile(weights_path)
AssertionError
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 440, in parallel_build
future.result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 451, in result
return self.__get_result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
raise self._exception
AssertionError
[TensorRT-LLM] TensorRT-LLM version: 0.16.0
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/process.py", line 246, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 390, in build_and_save
engine = build_model(build_config,
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 360, in build_model
model = model_cls.from_checkpoint(ckpt_dir, config=rank_config)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/models/modeling_utils.py", line 642, in from_checkpoint
assert os.path.isfile(weights_path)
AssertionError
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 440, in parallel_build
future.result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 451, in result
return self.__get_result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
raise self._exception
AssertionError
[TensorRT-LLM] TensorRT-LLM version: 0.16.0
[TensorRT-LLM] TensorRT-LLM version: 0.16.0
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/process.py", line 246, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 390, in build_and_save
engine = build_model(build_config,
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 360, in build_model
model = model_cls.from_checkpoint(ckpt_dir, config=rank_config)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/models/modeling_utils.py", line 642, in from_checkpoint
assert os.path.isfile(weights_path)
AssertionError
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 440, in parallel_build
future.result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 451, in result
return self.__get_result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
raise self._exception
AssertionError
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/process.py", line 246, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 390, in build_and_save
engine = build_model(build_config,
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 360, in build_model
model = model_cls.from_checkpoint(ckpt_dir, config=rank_config)
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/models/modeling_utils.py", line 642, in from_checkpoint
assert os.path.isfile(weights_path)
AssertionError
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 440, in parallel_build
future.result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 451, in result
return self.__get_result()
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
raise self._exception
AssertionError
Traceback (most recent call last):
File "/root/miniconda3/envs/deepseek_v3_2/bin/trtllm-build", line 8, in
sys.exit(main())
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 627, in main
parallel_build(model_config, ckpt_dir, build_config, args.output_dir,
File "/root/miniconda3/envs/deepseek_v3_2/lib/python3.10/site-packages/tensorrt_llm/commands/build.py", line 444, in parallel_build
assert len(exceptions
AssertionError: Engine building failed, please check error log.