[Bug] Fix out-of-range token id crashing tp=1 VocabParallelEmbedding#27482
Merged
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
…-oob # Conflicts: # python/sglang/srt/utils/async_probe.py
VocabParallelEmbedding
Collaborator
Author
|
/tag-and-rerun-ci extra |
4 tasks
monkeyLoveding
pushed a commit
to monkeyLoveding/sglang_open
that referenced
this pull request
Jun 9, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
gen_radix_treebuilds requests withrandom.randint(0, 32000)(inclusive), which can emit token id32000-- out of range for a 32000-vocab model (valid0..31999)tp=1,VocabParallelEmbedding.forwarddoes not mask input ids, so the bad id reachesF.embeddingand crashes with avectorized_gather_kerneldevice-side assertTestEagleLlama2Retract.test_radix_attentionFix
gen_radix_tree:random.randint(0, 31999)-- fix the off-by-oneVocabParallelEmbedding.forward: gatedmaybe_detect_oobon the input ids, so an out-of-range or negative (unmasked sentinel) id surfaces as a located assert instead of a silent OOB / coredumpmaybe_detect_oob: assert lower and upper bounds separately so the message names which one failedCI States
Latest PR Test (Base): 🚫 Run #27084365414
Latest PR Test (Extra): ❌ Run #27084365398