Skip to content

Add an argument to TpuPlatform.get_attn_backend_cls to adopt interfac… #1263

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
QiliangCui merged 2 commits into from
Dec 8, 2025
Merged

Add an argument to TpuPlatform.get_attn_backend_cls to adopt interfac… #1263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0c6414d
Add an argument to TpuPlatform.get_attn_backend_cls to adopt interfac…
QiliangCui Dec 8, 2025
3a911aa
Fix lora test failure.
QiliangCui Dec 8, 2025
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
2 changes: 1 addition & 1 deletion tests/lora/test_layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
ReplicatedLinearWithLoRA,
RowParallelLinearWithLoRA)
# yapf: enable
from vllm.lora.models import LoRALayerWeights, PackedLoRALayerWeights
from vllm.lora.lora_weights import LoRALayerWeights, PackedLoRALayerWeights
from vllm.lora.punica_wrapper import get_punica_wrapper
from vllm.model_executor.layers.linear import (ColumnParallelLinear,
MergedColumnParallelLinear,
Expand Down
3 changes: 2 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 @@ -55,7 +55,8 @@ def get_attn_backend_cls(cls, selected_backend: "AttentionBackendEnum",
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, attn_type: Any) -> str:
use_sparse: bool, use_mm_prefix: bool,
attn_type: Any) -> str:
from vllm.attention.backends.registry import AttentionBackendEnum
if selected_backend != AttentionBackendEnum.PALLAS:
logger.info("Cannot use %s backend on TPU.", selected_backend)
Expand Down