[Bug]在910B上量化后部署好无法正常访问

[jxz542189]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

当前环境：910B机器（x86_64)

运行AWQ量化(lmdeploy lite auto_awq DeepSeek-R1-Distill-Qwen-7B --work-dir DeepSeek-R1-Distill-Qwen-7B-AWQ-0301-v1.0 --device npu)，可以正常部署（lmdeploy serve api_server DeepSeek-R1-Distill-Qwen-7B-AWQ-0301-v1.0 --backend pytorch --device ascend --model-format awq --server-port 8005 --model-name deepseek-r1-distill-qwen-7B-awq --session-len 16000），但是无法正常访问：

2025-03-03 03:37:07,235 - lmdeploy - ERROR - engine.py:912 - Task failed
Traceback (most recent call last):
File "/opt/lmdeploy/lmdeploy/pytorch/engine/engine.py", line 907, in __task_callback
task.result()
File "/opt/lmdeploy/lmdeploy/pytorch/engine/engine.py", line 865, in _async_loop_background
await self._async_step_background(
File "/opt/lmdeploy/lmdeploy/pytorch/engine/engine.py", line 735, in _async_step_background
output = await self._async_model_forward(inputs,
File "/opt/lmdeploy/lmdeploy/utils.py", line 243, in __tmp
return (await func(*args, **kwargs))
File "/opt/lmdeploy/lmdeploy/pytorch/engine/engine.py", line 633, in _async_model_forward
ret = await __forward(inputs)
File "/opt/lmdeploy/lmdeploy/pytorch/engine/engine.py", line 610, in __forward
return await self.model_agent.async_forward(inputs, swap_in_map=swap_in_map, swap_out_map=swap_out_map)
File "/opt/lmdeploy/lmdeploy/pytorch/engine/model_agent.py", line 260, in async_forward
output = self._forward_impl(inputs, swap_in_map=swap_in_map, swap_out_map=swap_out_map)
File "/opt/lmdeploy/lmdeploy/pytorch/engine/model_agent.py", line 243, in _forward_impl
output = model_forward(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/opt/lmdeploy/lmdeploy/pytorch/engine/model_agent.py", line 151, in model_forward
output = model(**input_dict)
File "/opt/lmdeploy/lmdeploy/pytorch/backends/graph_runner.py", line 24, in call
return self.model(**kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/eval_frame.py", line 451, in _fn
return fn(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/convert_frame.py", line 921, in catch_errors
return callback(frame, cache_entry, hooks, frame_state, skip=1)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/convert_frame.py", line 400, in _convert_frame_assert
return _compile(
File "/usr/local/python3.10.5/lib/python3.10/contextlib.py", line 79, in inner
return func(*args, **kwds)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/convert_frame.py", line 676, in _compile
guarded_code = compile_inner(code, one_graph, hooks, transform)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/convert_frame.py", line 535, in compile_inner
out_code = transform_code_object(code, transform)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/bytecode_transformation.py", line 1036, in transform_code_object
transformations(instructions, code_options)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/convert_frame.py", line 165, in _fn
return fn(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/convert_frame.py", line 500, in transform
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 2149, in run
super().run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1272, in CALL_FUNCTION_KW
self.call_function(fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/nn_module.py", line 336, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1260, in CALL_FUNCTION_EX
self.call_function(fn, argsvars.items, kwargsvars)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 335, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 289, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 90, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1272, in CALL_FUNCTION_KW
self.call_function(fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/nn_module.py", line 336, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1260, in CALL_FUNCTION_EX
self.call_function(fn, argsvars.items, kwargsvars)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 335, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 289, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 90, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1272, in CALL_FUNCTION_KW
self.call_function(fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/nn_module.py", line 336, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1260, in CALL_FUNCTION_EX
self.call_function(fn, argsvars.items, kwargsvars)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 335, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 289, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 90, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1219, in CALL_FUNCTION
self.call_function(fn, args, {})
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 335, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 289, in call_function
return super().call_function(tx, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/functions.py", line 90, in call_function
return tx.inline_user_function_return(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 680, in inline_user_function_return
return InliningInstructionTranslator.inline_call(self, fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2285, in inline_call
return cls.inline_call(parent, func, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/dynamo/symbolic_convert.py", line 2399, in inline_call
tracer.run()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 810, in run
and self.step()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 489, in wrapper
return inner_fn(self, inst)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 1272, in CALL_FUNCTION_KW
self.call_function(fn, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/symbolic_convert.py", line 674, in call_function
self.push(fn.call_function(self, args, kwargs))
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/misc.py", line 562, in call_function
return self.obj.call_method(tx, self.name, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch_npu/utils/_dynamo.py", line 106, in TensorVariable_call_method
return TensorVariable.call_method_raw(self, tx, name, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/tensor.py", line 442, in call_method
return wrap_fx_proxy(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/builder.py", line 1330, in wrap_fx_proxy
return wrap_fx_proxy_cls(target_cls=TensorVariable, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/variables/builder.py", line 1415, in wrap_fx_proxy_cls
example_value = get_fake_value(proxy.node, tx, allow_non_graph_fake=True)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 1714, in get_fake_value
raise TorchRuntimeError(str(e)).with_traceback(e.traceback) from None
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 1656, in get_fake_value
ret_val = wrap_fake_exception(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 1190, in wrap_fake_exception
return fn()
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 1657, in
lambda: run_node(tx.output, node, args, kwargs, nnmodule)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 1782, in run_node
raise RuntimeError(make_error_message(e)).with_traceback(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_dynamo/utils.py", line 1766, in run_node
return getattr(args[0], node.target)(*args[1:], **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_tensor.py", line 921, in split
return torch._VF.split_with_sizes(self, split_size, dim)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/utils/_stats.py", line 20, in wrapper
return fn(*args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_subclasses/fake_tensor.py", line 896, in torch_dispatch
return self.dispatch(func, types, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_subclasses/fake_tensor.py", line 1241, in dispatch
return self._cached_dispatch_impl(func, types, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_subclasses/fake_tensor.py", line 974, in _cached_dispatch_impl
output = self._dispatch_impl(func, types, args, kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_subclasses/fake_tensor.py", line 1393, in _dispatch_impl
return decomposition_table[func](args, **kwargs)
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/_decomp/decompositions.py", line 1316, in split_with_sizes
torch._check_with(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/init.py", line 1123, in _check_with
raise error_type(message_evaluated)
torch._dynamo.exc.TorchRuntimeError: Failed running call_method split((FakeTensor(..., device='npu:0', size=(s0, 576), dtype=torch.float16), (3584, 512, 512)), **{'dim': -1}):
Split sizes add up to 4608 but got the tensor's size of 576

from user code:
File "/opt/lmdeploy/lmdeploy/pytorch/models/qwen2.py", line 324, in forward
hidden_states = self.model(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/opt/lmdeploy/lmdeploy/pytorch/models/qwen2.py", line 264, in forward
hidden_states, residual = decoder_layer(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/opt/lmdeploy/lmdeploy/pytorch/models/qwen2.py", line 188, in forward
hidden_states = self.self_attn(
File "/usr/local/python3.10.5/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/opt/lmdeploy/lmdeploy/pytorch/models/qwen2.py", line 73, in forward
query_states, key_states, value_states = self.qkv_proj.split_qkv(qkv_states)
File "/opt/lmdeploy/lmdeploy/pytorch/nn/linear.py", line 60, in split_qkv
q, k, v = x.split(sections, dim=-1)

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

You can suppress this exception and fall back to eager by setting:
import torch._dynamo
torch._dynamo.config.suppress_errors = True

2025-03-03 03:37:07,728 - lmdeploy - ERROR - async_engine.py:791 - session 1 finished, reason "error"
INFO: 172.17.0.1:60900 - "POST /v1/chat/completions HTTP/1.1" 200 OK

Reproduction

curl -s http://localhost:8005/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "deepseek-r1-distill-qwen-7B-awq",
"messages": [
{"role": "system", "content": "你是一个数学家."},
{"role": "user", "content": "1+2+3+4…+2025"}
],
"max_tokens": 10000,
"temperature": 0
}'

Environment

absl-py==2.1.0
accelerate==1.4.0
addict==2.4.0
aiohappyeyeballs==2.4.6
aiohttp==3.11.13
aiosignal==1.3.2
annotated-types==0.7.0
anyio==4.8.0
async-timeout==5.0.1
attr==0.3.2
attrs==25.1.0
auto_tune @ file:///root/selfgz859226207/compiler/lib64/auto_tune-0.1.0-py3-none-any.whl#sha256=8f08449dc1164e46c73acc85087e32a503ff77f4047d9b2c3f9597012e8adfb3
certifi==2025.1.31
cffi==1.17.1
charset-normalizer==3.4.1
click==8.1.8
cloudpickle==3.1.1
cmake==3.31.4
dataflow @ file:///root/selfgz859226207/compiler/lib64/dataflow-0.0.1-py3-none-any.whl#sha256=61d02556a49d4a5fa86ca434292c3733448fe3f62be337496414ce809c196215
datasets==2.16.0
decorator==5.2.1
dill==0.3.7
diskcache==5.6.3
distro==1.9.0
-e git+https://github.com/DeepLink-org/dlinfer.git@06f8580ae26768e982444a3937fcb64887291e60#egg=dlinfer_ascend
einops==0.8.1
exceptiongroup==1.2.2
fastapi==0.115.8
filelock==3.13.1
fire==0.7.0
frozenlist==1.5.0
fsspec==2023.10.0
h11==0.14.0
hccl @ file:///root/selfgz2398513867/hccl/lib64/hccl-0.1.0-py3-none-any.whl#sha256=0bfe7f1863fd4c3f056c0cdf806834764594c3254ec260e70255da87f7b12a94
hccl_parser @ file:///usr/local/Ascend/ascend-toolkit/8.0.0/toolkit/tools/hccl_parser-0.1-py3-none-any.whl#sha256=37541281a74de6ae3f8a15c77e1df8cf899bcbeb391a9a47ecfb582caf695fd8
httpcore==1.0.7
httpx==0.28.1
huggingface-hub==0.29.1
idna==3.10
interegular==0.3.3
Jinja2==3.1.4
jiter==0.8.2
jsonschema==4.23.0
jsonschema-specifications==2024.10.1
lark==1.2.2
llm_datadist @ file:///root/selfgz859226207/compiler/lib64/llm_datadist-0.0.1-py3-none-any.whl#sha256=7893ce8709f56d8d06f3d8b64f68b6c8e51a1e571e0d671e6be5bec99d6977a9
llvmlite==0.44.0
-e git+https://github.com/InternLM/lmdeploy@0eb625fa5059d8a1815b1747dbb4bb10e08a6836#egg=lmdeploy
markdown-it-py==3.0.0
MarkupSafe==2.1.5
mdurl==0.1.2
ml_dtypes==0.5.1
mmengine-lite==0.10.6
mpmath==1.3.0
msobjdump @ file:///usr/local/Ascend/ascend-toolkit/8.0.0/toolkit/tools/msobjdump-0.1.0-py3-none-any.whl#sha256=7bfe4926d56b034b7c19dca614b040b732bde240dafb7dcddce195596dabb600
multidict==6.1.0
multiprocess==0.70.15
nest-asyncio==1.6.0
networkx==3.3
ninja==1.11.1.3
numba==0.61.0
numpy==1.24.0
op_compile_tool @ file:///root/selfgz859226207/compiler/lib64/op_compile_tool-0.1.0-py3-none-any.whl#sha256=6c2d27cab88e642baa565cf3093e5c057300b32f68e83ebca34f136126a69e92
op_gen @ file:///usr/local/Ascend/ascend-toolkit/8.0.0/toolkit/tools/op_gen-0.1-py3-none-any.whl#sha256=243815003fd38a68940ad3de96fdd5fac3a465c32e4a834772f69b4c3c216234
op_test_frame @ file:///usr/local/Ascend/ascend-toolkit/8.0.0/toolkit/tools/op_test_frame-0.1-py3-none-any.whl#sha256=ff966bcad4e85cabebbebe368a808724069c909837cc210e4bd9cfe74bb25e33
opc_tool @ file:///root/selfgz859226207/compiler/lib64/opc_tool-0.1.0-py3-none-any.whl#sha256=85eab59b3a9225f65558d8f498c06988e3523714c16de8fb8f44b21f483fd5ff
openai==1.64.0
outlines==0.0.46
packaging==24.2
pandas==2.2.3
pathlib2==2.3.7.post1
peft==0.14.0
pillow==11.0.0
platformdirs==4.3.6
propcache==0.3.0
protobuf==5.29.3
psutil==7.0.0
pyairports==2.1.1
pyarrow==19.0.1
pyarrow-hotfix==0.6
pycountry==24.6.1
pycparser==2.22
pydantic==2.10.6
pydantic_core==2.27.2
Pygments==2.19.1
python-dateutil==2.9.0.post0
pytz==2025.1
PyYAML==6.0.2
referencing==0.36.2
regex==2024.11.6
requests==2.32.3
rich==13.9.4
rpds-py==0.23.1
safetensors==0.5.3
schedule_search @ file:///root/selfgz859226207/compiler/lib64/schedule_search-0.1.0-py3-none-any.whl#sha256=dcd6b3e218d353172396cdd6b299c8ddf28b638533a037bedb2ab0526fecf700
scikit-build==0.18.0
scipy==1.15.2
sentencepiece==0.2.0
shortuuid==1.0.13
show_kernel_debug_data @ file:///usr/local/Ascend/ascend-toolkit/8.0.0/toolkit/tools/show_kernel_debug_data-0.1.0-py3-none-any.whl#sha256=9d0d08c761209b32f4d38b6555b76f87c2ec49a9130f1039ae45cc8d0b7f5363
six==1.17.0
sniffio==1.3.1
starlette==0.45.3
sympy==1.13.3
te @ file:///root/selfgz859226207/compiler/lib64/te-0.4.0-py3-none-any.whl#sha256=6d03aed35fc22ecad63a6217043ec03d75e96410a6fcfa2944447959b86c9de0
termcolor==2.5.0
tiktoken==0.9.0
timm==1.0.15
tokenizers==0.21.0
tomli==2.2.1
torch==2.3.1+cpu
torch-npu==2.3.1
torchvision==0.18.1+cpu
tornado==6.4.2
tqdm==4.67.1
transformers==4.49.0
triton==3.1.0
typing_extensions==4.12.2
tzdata==2025.1
urllib3==2.3.0
uvicorn==0.34.0
xxhash==3.5.0
yapf==0.43.0
yarl==1.18.3

Error traceback

[jinminxi104]

量化的图模式还在开发中。这个w4a16请用eager=True。