[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
parent
484c211fe8
commit
d881812500
@@ -6,7 +6,7 @@ from typing import TYPE_CHECKING, Any, Union
|
||||
import torch
|
||||
from safetensors.torch import _TYPES as _SAFETENSORS_TO_TORCH_DTYPE
|
||||
from torch.nn import Parameter
|
||||
from transformers import PretrainedConfig
|
||||
from transformers import PreTrainedConfig
|
||||
|
||||
import vllm.model_executor.layers.fused_moe # noqa
|
||||
from vllm import _custom_ops as ops
|
||||
@@ -370,7 +370,7 @@ class AutoAWQConfig(QuantizationConfig):
|
||||
def maybe_update_config(
|
||||
self,
|
||||
model_name: str,
|
||||
hf_config: PretrainedConfig | None = None,
|
||||
hf_config: PreTrainedConfig | None = None,
|
||||
revision: str | None = None,
|
||||
):
|
||||
if self.modules_to_not_convert:
|
||||
|
||||
@@ -6,7 +6,7 @@ from typing import Any
|
||||
|
||||
import torch
|
||||
from safetensors.torch import _TYPES as _SAFETENSORS_TO_TORCH_DTYPE
|
||||
from transformers import PretrainedConfig
|
||||
from transformers import PreTrainedConfig
|
||||
|
||||
import vllm.model_executor.layers.fused_moe # noqa
|
||||
from vllm.logger import init_logger
|
||||
@@ -273,7 +273,7 @@ class AutoGPTQConfig(QuantizationConfig):
|
||||
def maybe_update_config(
|
||||
self,
|
||||
model_name: str,
|
||||
hf_config: PretrainedConfig | None = None,
|
||||
hf_config: PreTrainedConfig | None = None,
|
||||
revision: str | None = None,
|
||||
):
|
||||
if self.modules_in_block_to_quantize:
|
||||
|
||||
@@ -8,7 +8,7 @@ from typing import TYPE_CHECKING, Any
|
||||
import regex as re
|
||||
import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
from transformers import PreTrainedConfig
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from vllm.model_executor.layers.quantization import QuantizationMethods
|
||||
@@ -265,7 +265,7 @@ class QuantizationConfig(ABC):
|
||||
def maybe_update_config( # noqa: B027
|
||||
self,
|
||||
model_name: str,
|
||||
hf_config: PretrainedConfig | None = None,
|
||||
hf_config: PreTrainedConfig | None = None,
|
||||
revision: str | None = None,
|
||||
):
|
||||
"""Interface to update values after config initialization.
|
||||
|
||||
Reference in New Issue
Block a user