[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:
Harry Mellor
2026-09-24 14:14:10 +00:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 484c211fe8
commit d881812500
218 changed files with 869 additions and 813 deletions
@@ -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: