[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
@@ -3,7 +3,7 @@
import torch
import torch.nn as nn
from transformers import PretrainedConfig
from transformers import PreTrainedConfig
from vllm.config.lora import LoRAConfig
from vllm.distributed import (
@@ -85,7 +85,7 @@ class LogitsProcessorWithLoRA(BaseLayerWithLoRA):
self,
max_loras: int,
lora_config: LoRAConfig,
model_config: PretrainedConfig | None = None,
model_config: PreTrainedConfig | None = None,
) -> None:
# TODO: Verify if this condition can be further relaxed
if self.base_layer.vocab_size > 258048:
@@ -221,7 +221,7 @@ class LogitsProcessorWithLoRA(BaseLayerWithLoRA):
source_layer: nn.Module,
lora_config: LoRAConfig,
packed_modules_list: list,
model_config: PretrainedConfig | None = None,
model_config: PreTrainedConfig | None = None,
) -> bool:
# Special handling for the LogitsProcessor.
return False