Skip to content

[Bugfix] Fixed wrong class attribute assignment #7586

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
LookAround0301 wants to merge 11 commits into
base: main
Choose a base branch
from
Open

[Bugfix] Fixed wrong class attribute assignment #7586

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
0c206fa
[Bugfix] Fixed wrong class attribute assignment; use instance attribu…
LookAround0301 Mar 24, 2026
f87cef5
[Bugfix] remove ClassVar
LookAround0301 Mar 24, 2026
f9191c1
[Bugfix] remove ClassVar
LookAround0301 Mar 24, 2026
67b3fd4
[Bugfix] fix lint problem
LookAround0301 Mar 24, 2026
8cddff0
[Bugfix] fix lint problem
LookAround0301 Mar 24, 2026
2996049
[Bugfix] fix lint problem
LookAround0301 Mar 24, 2026
55de45b
[Bugfix] fix lint problem
LookAround0301 Mar 24, 2026
877c74d
Update vllm_ascend/attention/attention_v1.py
MengqingCao Mar 24, 2026
399e081
Update vllm_ascend/attention/attention_v1.py
MengqingCao Mar 24, 2026
61727f5
Apply suggestion from @MengqingCao
MengqingCao Mar 24, 2026
ecd448f
Update vllm_ascend/attention/attention_v1.py
MengqingCao Mar 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions vllm_ascend/attention/attention_v1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@

from dataclasses import dataclass
from enum import Enum
from typing import ClassVar

import torch
import torch_npu
Expand Down Expand Up @@ -213,7 +212,7 @@ class AscendAttentionMetadataBuilder(AttentionMetadataBuilder[AscendMetadata]):
# Does this backend/builder reorder the batch?
# If not, set this to None. Otherwise set it to the query
# length that will be pulled into the front of the batch.
reorder_batch_threshold: ClassVar[int] = 1
reorder_batch_threshold: int = 1

def __init__(
self,
Expand Down Expand Up @@ -242,7 +241,7 @@ def __init__(
got {self.decode_threshold}"
)

AscendAttentionMetadataBuilder.reorder_batch_threshold = self.decode_threshold
self.reorder_batch_threshold = self.decode_threshold

scheduler_config = vllm_config.scheduler_config
self.chunked_prefill_enabled = scheduler_config.enable_chunked_prefill
Expand Down
7 changes: 0 additions & 7 deletions vllm_ascend/attention/context_parallel/attention_cp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,6 @@
# This file is a part of the vllm-ascend project.
#

from typing import ClassVar

import numpy as np
import torch
import torch.distributed as dist
Expand Down Expand Up @@ -61,11 +59,6 @@ class AscendAttentionCPMetadataBuilder(AscendAttentionMetadataBuilder):
Extends AscendAttentionMetadataBuilder with PCP/DCP metadata handling.
"""

# Does this backend/builder reorder the batch?
# If not, set this to None. Otherwise set it to the query
# length that will be pulled into the front of the batch.
reorder_batch_threshold: ClassVar[int] = 1

def __init__(
self,
kv_cache_spec: AttentionSpec,
Expand Down
Loading