feat: Enable PyTorch2 Batching - #196
Merged
Merged
Conversation
20 tasks
mattwittwer
changed the title
mattwittwer
changed the title
whoisj
reviewed
Jun 4, 2026
yinggeh
previously approved these changes
Jun 8, 2026
pskiran1
previously approved these changes
Jun 9, 2026
whoisj
previously approved these changes
Jun 9, 2026
mattwittwer
dismissed stale reviews from whoisj, pskiran1, and yinggeh
via
June 9, 2026 20:57
6c047da
yinggeh
previously approved these changes
Jun 9, 2026
yinggeh
approved these changes
Jun 10, 2026
whoisj
approved these changes
Jun 11, 2026
mc-nv
pushed a commit
that referenced
this pull request
Jun 11, 2026
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
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does the PR do?
Enables default (first‑dimension) batching and sequence batching for the AOT Inductor (PT2) backend. Fixes the output responder to scatter batched results per‑request (first_dim_batching), implements control‑input + implicit‑state validation/registration and adds an io_data alias mechanism so control/state tensors resolve via ordinal (INPUT__N), forward (ARGS[...]), or descriptive (__) names - matching pt1.
Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
triton-inference-server/server#8814
Where should the reviewer start?
Test plan:
Caveats:
Background
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)