frozenleaves/DeepSpeed
1
0
Fork 0
mirror of https://github.com/deepspeedai/DeepSpeed.git synced 2025-11-11 16:50:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix extra_repr_str when weight is None / in zero-3 (#7254)

Browse Source 
extra_repr_str will be undefined if self.weight is None with current
code.

In addition, the shape is stored in ds_shape if it's in ZeRO-3, so we
also need to do this check (Although currently AutoTP hasn't supported
ZeRO-3).

```logs
  File "deepspeed/__init__.py", line 394, in tp_model_init
    model = TpTrainingManager(model=model, tp_size=tp_size, dtype=dtype).module
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/runtime/tensor_parallel/tp_manager.py", line 35, in __init__
    self._apply_policies(parser_dict)
  File "deepspeed/runtime/tensor_parallel/tp_manager.py", line 47, in _apply_policies
    self._apply_injection_policy(self.config, client_module)
  File "deepspeed/runtime/tensor_parallel/tp_manager.py", line 53, in _apply_injection_policy
    replace_transformer_layer(client_module, self.module, None, self.config, self.model_config)
  File "deepspeed/module_inject/replace_module.py", line 400, in replace_transformer_layer
    replaced_module = replace_module(model=model,
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/replace_module.py", line 653, in replace_module
    replaced_module, _ = _replace_module(model, policy, state_dict=sd)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/replace_module.py", line 713, in _replace_module
    _, layer_id = _replace_module(child,
                  ^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/replace_module.py", line 713, in _replace_module
    _, layer_id = _replace_module(child,
                  ^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/replace_module.py", line 689, in _replace_module
    replaced_module = policies[child.__class__][0](child,
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/replace_module.py", line 333, in replace_fn
    new_module = replace_wo_policy(child, _policy, prefix=prefix, state_dict=state_dict)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/replace_module.py", line 316, in replace_wo_policy
    return _autotp._replace_module(module)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/auto_tp.py", line 481, in _replace_module
    self._replace_module(child, name, class_name)
  File "deepspeed/module_inject/auto_tp.py", line 466, in _replace_module
    setattr(r_module, name, self.linear_policies[child.__class__](child, prev_name + '.' + name,
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/auto_tp.py", line 361, in _replace
    if 'Yuan' in str(self.module):
                 ^^^^^^^^^^^^^^^^
  File "torch/nn/modules/module.py", line 2940, in __repr__
    mod_str = repr(module)
              ^^^^^^^^^^^^
  File "torch/nn/modules/module.py", line 2940, in __repr__
    mod_str = repr(module)
              ^^^^^^^^^^^^
  File "torch/nn/modules/module.py", line 2934, in __repr__
    extra_repr = self.extra_repr()
                 ^^^^^^^^^^^^^^^^^
  File "deepspeed/module_inject/layers.py", line 267, in extra_repr
    out_features, in_features = self.weight.shape[-2:] if self.weight is not None else (None, None)
    ^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 1)
```

Signed-off-by: Hollow Man <hollowman@opensuse.org>
Co-authored-by: Logan Adams <114770087+loadams@users.noreply.github.com>
This commit is contained in:
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
2025-05-22 12:01:12 +08:00
committed by GitHub
parent e290bf580d
commit 0e3209a16b
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
deepspeed/module_inject/layers.py
View File

@ -10,6 +10,7 @@ from torch.nn import functional as F
from torch.nn.parameter import Parameter
from deepspeed.accelerator import get_accelerator
from deepspeed.module_inject.tp_shard import get_shard_size, get_shard_size_list
from deepspeed.runtime.zero.utils import is_zero_param
from abc import ABC, abstractmethod
from typing import Iterable, Any, Optional, List, Tuple
from .fusedqkv_utils import shard_value_with_share_qk, shard_chunk_mlp, prepare_tp_fused_qkvw
@ -262,12 +263,13 @@ class TensorParallel_Layer(nn.Module, ABC):
return new_obj
def extra_repr(self):
out_features, in_features = None, None
if self.weight is not None:
out_features, in_features = self.weight.shape[-2:] if self.weight is not None else (None, None)
dtype = self.weight.dtype if self.weight is not None else None
extra_repr_str = "in_features={}, out_features={}, bias={}, dtype={}".format(
in_features, out_features, self.bias is not None, dtype)
return extra_repr_str
out_features, in_features = self.weight.ds_shape[-2:] if is_zero_param(
self.weight) else self.weight.shape[-2:]
dtype = self.weight.dtype if self.weight is not None else None
return "in_features={}, out_features={}, bias={}, dtype={}".format(in_features, out_features, self.bias
is not None, dtype)
def move(self, tensor):
# TODO: consider the timing of deletion