Add opt-in Wired Memory - #6
Open
ronaldmannak wants to merge 5 commits into
Open
Conversation
ronaldmannak
force-pushed
the
layr/wiredmemory
branch
from
May 10, 2026 04:14
93cb916 to
f2c2b5b
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add an opt-in Wired Memory execution boundary for continuous batching.
BatchGeneratornow has adrain(wiredMemoryTicket:onResponse:)convenience method that holds aWiredMemoryTicketacross the full drain loop, rather than starting and ending the ticket for eachnext()step. The low-levelnext()API remains synchronous.Changes
BatchGenerator.drain(wiredMemoryTicket:onResponse:).insert,cancel,next, orcloseconcurrently withdrain.Notes
Ticket sizing remains caller-owned in this PR. Automatic continuous-batch memory estimation is intentionally left for a future scheduler/container layer because it depends on cache topology, prompt shape,
completionBatchSize, and admission policy.