File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/runner/layer_wise_runner.py", line 72, in run [0/1910]
self.generated_schedule(process_unit, data_recorder)
File "/usr/local/lib64/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/runner/generated_runner.py", line 200, in generated_schedule
if not unit.make_progress():
^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/runner/generated_runner.py", line 99, in make_progress
self.processor.process(batch_request)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/quant/processor/base.py", line 116, in process
super().process(request)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/base/processor.py", line 43, in process
self._run_forward_if_need(request)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/base/processor.py", line 75, in _run_forward_if_need
output = request.module(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1568, in _call_impl
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/DeepSeek-R1-0528/modeling_deepseek.py", line 1202, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/DeepSeek-R1-0528/modeling_deepseek.py", line 769, in forward
q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1568, in _call_impl
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Float8_e4m3fn has not been supported
[ERROR] 2025-11-03-14:18:22 (PID:574, Device:0, RankID:-1) ERR01007 OPS feature not supported
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/usr/local/bin/msmodelslim", line 8, in <module>
sys.exit(main())
^^^^^^
File "/usr/local/lib/python3.11/site-packages/msmodelslim/cli/__main__.py", line 76, in main
quant_main(args)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/cli/naive_quantization/__main__.py", line 50, in main
app.quant(
File "/usr/local/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 277, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/msmodelslim/utils/exception_decorator.py", line 170, in wrapper
raise unexpected_error from e
msmodelslim.utils.exception.UnexpectedError: Code: 500, Message: Unexpected error.
TIP: Please report this issue to the msModelSlim developers. Repository: https://gitcode.com/Ascend/msit Q&A: https://gitcode.com/Ascend/msit/blob/master/msmodelslim/docs/FAQ.md
[ERROR] 2025-11-03-14:18:24 (PID:574, Device:0, RankID:-1) ERR99999 UNKNOWN application exception
swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:2.1.RC2-800I-A2-py311-openeuler24.03-lts
修改msit/msmodelslim/example/DeepSeek/quant_deepseek_w4a8.py
model = AutoModelForCausalLM.from_pretrained(pretrained_model_name_or_path=model_path,添加:
max_memory={0: "50GiB", 1: "50GiB", 2: "50GiB", 3: "50GiB",4: "50GiB", 5: "50GiB",6: "50GiB", 7: "50GiB","cpu": "1500GiB"},也未起作用,只用到一张卡
量化命令:
另外量化进行到半小时左右报类型错误:
File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/runner/layer_wise_runner.py", line 72, in run [0/1910] self.generated_schedule(process_unit, data_recorder) File "/usr/local/lib64/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/runner/generated_runner.py", line 200, in generated_schedule if not unit.make_progress(): ^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/runner/generated_runner.py", line 99, in make_progress self.processor.process(batch_request) File "/usr/local/lib/python3.11/site-packages/msmodelslim/quant/processor/base.py", line 116, in process super().process(request) File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/base/processor.py", line 43, in process self._run_forward_if_need(request) File "/usr/local/lib/python3.11/site-packages/msmodelslim/core/base/processor.py", line 75, in _run_forward_if_need output = request.module(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1568, in _call_impl result = forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/.cache/huggingface/modules/transformers_modules/DeepSeek-R1-0528/modeling_deepseek.py", line 1202, in forward hidden_states, self_attn_weights, present_key_value = self.self_attn( ^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/.cache/huggingface/modules/transformers_modules/DeepSeek-R1-0528/modeling_deepseek.py", line 769, in forward q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1568, in _call_impl result = forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/linear.py", line 114, in forward return F.linear(input, self.weight, self.bias) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Float8_e4m3fn has not been supported [ERROR] 2025-11-03-14:18:22 (PID:574, Device:0, RankID:-1) ERR01007 OPS feature not supported The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/usr/local/bin/msmodelslim", line 8, in <module> sys.exit(main()) ^^^^^^ File "/usr/local/lib/python3.11/site-packages/msmodelslim/cli/__main__.py", line 76, in main quant_main(args) File "/usr/local/lib/python3.11/site-packages/msmodelslim/cli/naive_quantization/__main__.py", line 50, in main app.quant( File "/usr/local/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 277, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/msmodelslim/utils/exception_decorator.py", line 170, in wrapper raise unexpected_error from e msmodelslim.utils.exception.UnexpectedError: Code: 500, Message: Unexpected error. TIP: Please report this issue to the msModelSlim developers. Repository: https://gitcode.com/Ascend/msit Q&A: https://gitcode.com/Ascend/msit/blob/master/msmodelslim/docs/FAQ.md [ERROR] 2025-11-03-14:18:24 (PID:574, Device:0, RankID:-1) ERR99999 UNKNOWN application exception