Repository navigation
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A 180-second PD handshake can expire while Decode is still within its configured resource wait. Derive the enclosing deadlines from the current segment's two resource-wait stages, leaving time for errors to propagate. A 200-second resource budget gives Master/Prefill deadlines of 415/430 seconds; negative budgets retain disconnect and cancellation checks. Busy retry is unchanged.
Validation on main 9640f76: 168 CPU tests pass. In a 32-request control-plane contention reproduction with slots released at 190 seconds and busy retry=0, main times out all 32 at 180 seconds; the fix lets all 32 continue. This probe uses the real wait/allocation loops with controlled slot availability, without model traffic.