Skip to content

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

Merged
QiliangCui merged 2 commits intomainfrom
dev1208
Dec 8, 2025
Merged

Add an argument to TpuPlatform.get_attn_backend_cls to adopt interfac…#1263
QiliangCui merged 2 commits intomainfrom
dev1208

Conversation

@QiliangCui
Copy link
Copy Markdown
Collaborator

@QiliangCui QiliangCui commented Dec 8, 2025

Description

Add an argument in get_attn_backend_cls to adopt the change in vllm-project/vllm#27938.

Fix lora test broken by https://github.com/vllm-project/vllm/pull/30253/files

FIXES: b/467049790

Tests

manually test:

VLLM_USE_V1=1 vllm serve Qwen/Qwen2.5-7B-Instruct \
 --seed 42 \
 --disable-log-requests \
 --max-num-seqs 128 \
 --max-num-batched-tokens 128 \
 --tensor-parallel-size 1 \
 --no-enable-prefix-caching \
 --download_dir /mnt/disks/persist \
 --max-model-len 64

before the change error about

TypeError: TpuPlatform.get_attn_backend_cls() takes 11 positional arguments but 12 were given

with the fix, vllm can start.

CIT

https://buildkite.com/tpu-commons/tpu-inference-ci/builds/6565

https://buildkite.com/tpu-commons/tpu-inference-ci/builds/6571

Checklist

Before submitting this PR, please make sure:

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have made or will make corresponding changes to any relevant documentation.

…e change.

Signed-off-by: Qiliang Cui <derrhein@gmail.com>
@github-actions
Copy link
Copy Markdown

github-actions bot commented Dec 8, 2025

Description

Start with a short description of what the PR does and how this is a change from
the past.

The rest of the description includes relevant details and context, examples:

  • why is this change being made,
  • the problem being solved and any relevant context,
  • why this is a good solution,
  • some information about the specific implementation,
  • shortcomings of the solution and possible future improvements.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Tests

Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

Before submitting this PR, please make sure:

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have made or will make corresponding changes to any relevant documentation.

Signed-off-by: Qiliang Cui <derrhein@gmail.com>
Copy link
Copy Markdown
Collaborator

@kyuyeunk kyuyeunk left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: rename this pr since it also includes fix for lora part as well.

@QiliangCui QiliangCui merged commit 0d4a4d1 into main Dec 8, 2025
25 checks passed
sixiang-google pushed a commit that referenced this pull request Dec 9, 2025
gpolovets1 pushed a commit that referenced this pull request Dec 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants