Skip to content

fix(attn): remove invalid attention param #305

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

Merged
rebel-jiwoopark merged 1 commit into from
Jan 28, 2026
Merged

fix(attn): remove invalid attention param #305

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 1 addition & 2 deletions vllm_rbln/attention/backends/flash_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@

import math
from dataclasses import dataclass
from typing import Any, Dict, List, Optional, Tuple, Type
from typing import Dict, List, Optional, Tuple, Type

import torch
from vllm.attention.backends.abstract import (AttentionBackend, AttentionImpl,
Expand Down Expand Up @@ -492,7 +492,6 @@ def __init__(
alibi_slopes: Optional[List[float]],
sliding_window: Optional[int],
kv_cache_dtype: str,
blocksparse_params: Optional[Dict[str, Any]] = None,
logits_soft_cap: Optional[float] = None,
attn_type: str = AttentionType.DECODER,
kv_sharing_target_layer_name: Optional[str] = None,
Expand Down
6 changes: 1 addition & 5 deletions vllm_rbln/v1/attention/backends/flash_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

import math
from dataclasses import dataclass
from typing import TYPE_CHECKING, Any, Optional
from typing import TYPE_CHECKING, Optional

import torch
from vllm.attention.backends.abstract import (AttentionBackend, AttentionImpl,
Expand Down Expand Up @@ -787,7 +787,6 @@ def __init__(
alibi_slopes: Optional[list[float]],
sliding_window: Optional[int],
kv_cache_dtype: str,
blocksparse_params: Optional[dict[str, Any]] = None,
logits_soft_cap: Optional[float] = None,
attn_type: str = AttentionType.DECODER,
kv_sharing_target_layer_name: Optional[str] = None,
Expand All @@ -799,9 +798,6 @@ def __init__(

if kv_sharing_target_layer_name is not None:
raise NotImplementedError("KV sharing is not supported in RBLN.")
if blocksparse_params is not None:
raise ValueError("RBLN Attention Backend does not "
"support block-sparse attention.")
if logits_soft_cap is not None:
logger.warning_once(
"RBLN Attention Backend does not support logits soft cap. "
Expand Down