biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Remove redundant config definitions (#21891)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-07-30 14:54:18 +08:00
committed by GitHub
parent 6f8d261882
commit 2ca5f82c2a
23 changed files with 54 additions and 1910 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/models/mpt.py
View File

@@ -8,6 +8,7 @@ from typing import Optional, Union
import torch
import torch.nn as nn
from transformers import PretrainedConfig
from vllm.attention import Attention
from vllm.compilation.decorators import support_torch_compile
@@ -25,7 +26,6 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
from vllm.transformers_utils.configs.mpt import MPTConfig
from .interfaces import SupportsPP
from .utils import (AutoWeightsLoader, is_pp_missing_parameter,
@@ -50,7 +50,7 @@ class MPTAttention(nn.Module):
def __init__(
self,
config: MPTConfig,
config: PretrainedConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
@@ -144,7 +144,7 @@ class MPTMLP(nn.Module):
def __init__(
self,
config: MPTConfig,
config: PretrainedConfig,
quant_config: Optional[QuantizationConfig] = None,
):
super().__init__()
@@ -176,7 +176,7 @@ class MPTBlock(nn.Module):
def __init__(
self,
config: MPTConfig,
config: PretrainedConfig,
cache_config: Optional[CacheConfig] = None,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",