Skip to content

Rename DSpark hidden protocol to PD hidden - #648

Merged
zhangxiaolei123456 merged 1 commit into
fix/dspark-review-dedupe-currentfrom
fix/pd-hidden-protocol-rename
Jul 20, 2026
Merged

zhangxiaolei123456 merged 1 commit into
fix/dspark-review-dedupe-currentfrom
fix/pd-hidden-protocol-rename

Conversation

@zhangxiaolei123456

@zhangxiaolei123456 zhangxiaolei123456 commented Jul 20, 2026 •

Copy link
Copy Markdown
Collaborator

Motivation

Modifications

Accuracy Tests

Speed Tests and Profiling

Checklist

Review and Merge Process

  1. Ping Merge Oncalls to start the process. See the PR Merge Process.
  2. Get approvals from CODEOWNERS and other reviewers.
  3. Trigger CI tests with comments or contact authorized users to do so.
    • Common commands include /tag-and-rerun-ci, /tag-run-ci-label, /rerun-failed-ci
  4. After green CI and required approvals, ask Merge Oncalls or people with Write permission to merge the PR.

CI States

Latest PR Test (Base): ❌ Run #29751733102
Latest PR Test (Extra): ❌ Run #29751732637

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Code Review

This pull request refactors the codebase to rename references of the 'DSpark' hidden protocol to 'PD' hidden protocol across various modules, including connection managers, schedulers, and model executors. The review feedback points out several missed renames that should be addressed for consistency, including endpoint string literals, methods like send_dspark_owner_direct_hidden_for_batch and _pp_maybe_send_dspark_owner_direct_hidden, and variables such as dspark_layers_to_capture and capture_dspark.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

self.pd_hidden_ack_completion_cv = threading.Condition()
self.pd_hidden_acked_chunks: Dict[int, List[dict]] = defaultdict(list)
self.pd_hidden_acked_lock = threading.Lock()
self.pd_hidden_ack_wakeup_endpoint = (

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The endpoint string literal still contains dspark-hidden-ack- while the variable name was renamed to self.pd_hidden_ack_wakeup_endpoint. For consistency with the renaming of the DSpark hidden protocol to PD hidden, this should be updated to pd-hidden-ack-.

written[local_start:local_end] = [True] * rows
if send_owner_direct:
self._send_dspark_hidden_only_chunk(req)
self._send_pd_hidden_only_chunk(req)

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The method send_dspark_owner_direct_hidden_for_batch was not renamed to send_pd_owner_direct_hidden_for_batch. For consistency with the renaming of the DSpark hidden protocol to PD hidden, please rename this method and all its references.

result: GenerationBatchResult,
) -> None:
if not self._pp_should_owner_direct_dspark_hidden(batch):
if not self._pp_should_owner_direct_pd_hidden(batch):

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The method _pp_maybe_send_dspark_owner_direct_hidden and the reference to send_dspark_owner_direct_hidden_for_batch were not renamed to use pd instead of dspark. For consistency, please rename them to _pp_maybe_send_pd_owner_direct_hidden and send_pd_owner_direct_hidden_for_batch respectively.


dspark_layers_to_capture = getattr(
forward_batch, "dspark_hidden_capture_layer_ids", None
forward_batch, "pd_hidden_capture_layer_ids", None

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The variable dspark_layers_to_capture was not renamed to pd_layers_to_capture. For consistency with the renaming of the DSpark hidden protocol to PD hidden, please rename this variable.

if capture_dspark:
for idx, aux_hidden in enumerate(dspark_aux_hidden_states):
proxy_tensors[f"dspark_aux_hidden_states_{idx}"] = (
for idx, aux_hidden in enumerate(pd_aux_hidden_states):

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The variable capture_dspark was not renamed to capture_pd. For consistency with the renaming of the DSpark hidden protocol to PD hidden, please rename this variable.

@zhangxiaolei123456
zhangxiaolei123456 merged commit f334074 into fix/dspark-review-dedupe-current Jul 20, 2026
72 of 82 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant