Skip to content

Conversation

@py4
Copy link
Collaborator

@py4 py4 commented Oct 31, 2025

No description provided.

@github-actions
Copy link

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.

@py4 py4 force-pushed the pooyam branch 2 times, most recently from 749fd74 to 00265e5 Compare October 31, 2025 05:27
@kyuyeunk
Copy link
Collaborator

kyuyeunk commented Nov 5, 2025

Awesome. If I understand correctly, it will now require an approval from one of the owners before it can be merged right?

Copy link
Collaborator

@vipannalla vipannalla left a comment

Choose a reason for hiding this comment

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

Thanks for the PR, I suggested few owner changes but LGTM lets merge and iterate forward.

Comment on lines +13 to +14
/.buildkite/ @jcyang43
/.github/ @jcyang43
Copy link
Collaborator

Choose a reason for hiding this comment

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

Can you also add @QiliangCui for CI/CD?

/tpu_inference/spec_decode/ @py4 @Lumosis

# Platform Support
/tpu_inference/platforms/ @xiangxu-google @lsy323
Copy link
Collaborator

Choose a reason for hiding this comment

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

Since Siyuan is leaving and Xiang is OOO for few months, can you probably add @wenxindongwork instead who is updating this for DP support.

/tpu_inference/runner/persistent_batch_manager.py @py4 @xiangxu-google
/tpu_inference/runner/speculative_decoding_manager.py @py4 @Lumosis
/tpu_inference/executors/ @xiangxu-google @mrjunwan-lang
/tpu_inference/core/ @sixiang-google
Copy link
Collaborator

Choose a reason for hiding this comment

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

Also add @mrjunwan-lang as secondary owner


# JAX Model Layers - Attention
/tpu_inference/layers/jax/ @py4 @bzgoogle @jrplatin @gpolovets1
/tpu_inference/layers/vllm/ @hfan @vanbasten23 @lsy323
Copy link
Collaborator

Choose a reason for hiding this comment

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

Similar to comment below, can you add me instead of Siyuan for various vLLM related things?

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