[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
+3 -3
View File
@@ -8,7 +8,7 @@ from typing import Any
import torch
import torch.nn.functional as F
from transformers import PretrainedConfig
from transformers import PreTrainedConfig
from vllm.config.model import AttnTypeStr, ModelConfig, ModelDType, RunnerOption
from vllm.config.pooler import SequencePoolingType, TokenPoolingType
@@ -446,12 +446,12 @@ def get_vllm_extra_kwargs(model_info: ModelInfo, vllm_extra_kwargs):
def dummy_hf_overrides(
hf_config: PretrainedConfig,
hf_config: PreTrainedConfig,
*,
model_arch: str = "",
exist_overrides: dict[str, Any] | None = None,
use_original_num_layers: bool = False,
) -> PretrainedConfig:
) -> PreTrainedConfig:
"""Dummy HF overrides function used to create dummy model
with only minimum nums of layer.
"""