Skip to content

[Bugfix] Fix attention backend signature #1103

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
kyuyeunk merged 1 commit into from
Nov 14, 2025
Merged

[Bugfix] Fix attention backend signature #1103

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
4 changes: 3 additions & 1 deletion tpu_inference/platforms/tpu_platform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
import vllm.envs as vllm_envs
from torchax.ops.mappings import j2t_dtype
from tpu_info import device
from vllm.attention.backends.abstract import AttentionType
from vllm.inputs import ProcessorInputs, PromptType
from vllm.platforms.interface import Platform, PlatformEnum
from vllm.sampling_params import SamplingParams, SamplingType
Expand Down Expand Up @@ -57,7 +58,8 @@ class TpuPlatform(Platform):
def get_attn_backend_cls(cls, selected_backend: "_Backend", head_size: int,
dtype: jnp.dtype, kv_cache_dtype: Optional[str],
block_size: int, use_v1: bool, use_mla: bool,
has_sink: bool, use_sparse: bool) -> str:
has_sink: bool, use_sparse: bool,
attn_type: AttentionType) -> str:
from vllm.attention.backends.registry import _Backend
if selected_backend != _Backend.PALLAS:
logger.info("Cannot use %s backend on TPU.", selected_backend)
Expand Down