fix: make inference and PD master recursion limits configurable - #1581
Merged
Merged
Conversation
shihaobai
requested review from
WANDY666,
blueswhen,
hiworldwzj and
sufubao
September 18, 2026 13:45
shihaobai
added a commit
that referenced
this pull request
Sep 18, 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Long contexts can exceed Python's recursion limit during radix-cache insertion and prefix matching. With 512-token small pages, a 1,048,576-token context needs roughly 2,048 recursive calls, exceeding the inference worker's default limit of 1,000.
Add cached readers in
envs_utils.pyforLIGHTLLM_MODEL_INFER_RECURSION_LIMITandLIGHTLLM_PD_MASTER_RECURSION_LIMIT, both defaulting to 4,000. Each inference rank applies its limit before starting worker threads, and PD Master's cache-aware configuration reads its independent limit when initialized.