[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:
co-authored by
Claude Opus 5.5
parent
484c211fe8
commit
d881812500
@@ -22,7 +22,7 @@ from typing import Any
|
||||
|
||||
import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
from transformers import PreTrainedConfig
|
||||
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
@@ -60,7 +60,7 @@ from .utils import (
|
||||
class LoopCoderAttention(nn.Module):
|
||||
def __init__(
|
||||
self,
|
||||
config: PretrainedConfig,
|
||||
config: PreTrainedConfig,
|
||||
hidden_size: int,
|
||||
num_heads: int,
|
||||
num_kv_heads: int,
|
||||
@@ -210,7 +210,7 @@ class LoopCoderAttention(nn.Module):
|
||||
class LoopCoderDecoderLayer(nn.Module):
|
||||
def __init__(
|
||||
self,
|
||||
config: PretrainedConfig,
|
||||
config: PreTrainedConfig,
|
||||
cache_config: CacheConfig | None = None,
|
||||
quant_config: QuantizationConfig | None = None,
|
||||
prefix: str = "",
|
||||
|
||||
Reference in New Issue
Block a user