[Misc] Use config definitions from Transformers library (#21913)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-08-08 23:10:51 -07:00
committed by GitHub
parent 7ad7adb67f
commit 65552b476b
11 changed files with 54 additions and 51 deletions
+7 -7
View File
@@ -6,7 +6,7 @@ from typing import Optional, Union
import torch
import torch.nn as nn
from transformers import PretrainedConfig
from transformers import DbrxConfig
from vllm.attention import Attention
from vllm.config import CacheConfig, VllmConfig
@@ -39,7 +39,7 @@ class DbrxRouter(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: DbrxConfig,
params_dtype: Optional[torch.dtype] = None,
):
super().__init__()
@@ -63,7 +63,7 @@ class DbrxExperts(FusedMoE):
def __init__(
self,
config: PretrainedConfig,
config: DbrxConfig,
quant_config: Optional[QuantizationConfig] = None,
params_dtype: Optional[torch.dtype] = None,
prefix: str = "",
@@ -138,7 +138,7 @@ class DbrxMoE(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: DbrxConfig,
quant_config: Optional[QuantizationConfig] = None,
params_dtype: Optional[torch.dtype] = None,
prefix: str = "",
@@ -169,7 +169,7 @@ class DbrxAttention(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: DbrxConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
@@ -249,7 +249,7 @@ class DbrxFusedNormAttention(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: DbrxConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
@@ -284,7 +284,7 @@ class DbrxBlock(nn.Module):
def __init__(
self,
config: PretrainedConfig,
config: DbrxConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",