Skip to content

Remove perfmetrics synchronization workaround - #4619

Merged
mzegla merged 1 commit into
mainfrom
remove_wa
Oct 2, 2026
Merged

mzegla merged 1 commit into
mainfrom
remove_wa

Conversation

@mzegla

@mzegla mzegla commented Oct 1, 2026

Copy link
Copy Markdown
Collaborator

Synchronized in GenAI, don't need special treatment in OVMS anymore

Copilot AI balanced review requested due to automatic review settings October 1, 2026 11:03

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Copilot review overview

🟢 Approval recommended

The pinned GenAI revision contains the required notification-ordering fix, and both call paths are updated consistently.

Review effort: Balanced
Findings: None

What changed in this PR

Removes obsolete OVMS polling now that GenAI publishes performance metrics before notifying generation consumers.

Changes:

  • Removes retry/yield helpers and unused thread headers.
  • Retrieves and logs LLM/VLM metrics directly.
File Description
src/​llm/​language_model/​continuous_batching/​servable.cpp Simplifies LLM metrics retrieval.
src/​llm/​visual_language_model/​continuous_batching/​servable.cpp Simplifies VLM metrics retrieval.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

@mzegla
mzegla merged commit d515e36 into main Oct 2, 2026
11 checks passed
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