[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
@@ -3,7 +3,7 @@
"""Inference-only IBM Granite Speech Plus model."""
import torch
from transformers import PretrainedConfig
from transformers import PreTrainedConfig
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.multimodal import MULTIMODAL_REGISTRY
@@ -68,7 +68,7 @@ class GraniteSpeechPlusForConditionalGeneration(GraniteSpeechForConditionalGener
def _build_encoder(
self,
config: PretrainedConfig,
config: PreTrainedConfig,
quant_config: QuantizationConfig | None,
prefix: str,
) -> GraniteSpeechCTCEncoder: