[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
@@ -5,7 +5,7 @@ from collections.abc import Callable, Iterable
import torch
import torch.nn as nn
from transformers.configuration_utils import PretrainedConfig
from transformers.configuration_utils import PreTrainedConfig
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, VllmConfig
@@ -79,7 +79,7 @@ class BailingMoeV25MLAAttention(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: PreTrainedConfig,
quant_config: QuantizationConfig | None = None,
layer_id: int = 0,
prefix: str = "attention",
@@ -234,7 +234,7 @@ class BailingMoeV25(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: PreTrainedConfig,
quant_config: QuantizationConfig | None = None,
layer_id: int = 0,
prefix: str = "",
@@ -349,7 +349,7 @@ class BailingMoeV25DecoderLayer(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: PreTrainedConfig,
vllm_config: VllmConfig,
prefix: str = "layer",
layer_id: int = 0,