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

[1/N][Attention] Restructure attention: move files (#31916)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-09 16:10:24 -05:00
committed by GitHub
parent 1f8b7c536b
commit 2612ba9285
195 changed files with 426 additions and 396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/minimax_text_01.py
View File

@@ -14,7 +14,6 @@ import torch
from torch import nn
from transformers import MiniMaxConfig
from vllm.attention.backends.abstract import AttentionMetadata
from vllm.attention.layer import Attention
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, ModelConfig, VllmConfig
@@ -48,6 +47,7 @@ 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.models.utils import maybe_prefix
from vllm.sequence import IntermediateTensors
from vllm.v1.attention.backend import AttentionMetadata
from .interfaces import HasInnerState, IsHybrid
from .utils import PPMissingLayer, is_pp_missing_parameter, make_layers