[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
+2 -2
View File
@@ -9,7 +9,7 @@ import torch
import torch.nn.functional as F
from torch import nn
from torch.nn import LayerNorm
from transformers.configuration_utils import PretrainedConfig
from transformers.configuration_utils import PreTrainedConfig
from transformers.modeling_utils import PreTrainedModel
from vllm.third_party.deep_gemm import per_block_cast_to_fp8
@@ -27,7 +27,7 @@ from .vision_attention import (
from .vision_moe import note_vision_fused_moe_fp8
class DotsMoEVitConfig(PretrainedConfig):
class DotsMoEVitConfig(PreTrainedConfig):
model_type: str = "dots_moe_vit"
def __init__(