Issue Station
Sign In
Tools hereToolbox

vllm - ✅(Solved) Fix [Doc]: scoring.md missing ModernBertForSequenceClassification from supported cross-encoder models [1 pull requests, 2 comments, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
vllm-project/vllm#41829•Fetched 2026-05-07 03:32:38
View on GitHub
Comments
2
Participants
1
Timeline
10
Reactions
0
Author
JLiu4CodingJLiu4Coding
Participants
JLiu4CodingJLiu4Coding
Assignees
JLiu4CodingJLiu4Coding
Timeline (top)
commented ×2mentioned ×2subscribed ×2assigned ×1

Fix Action

Fixed

PR fix notes

PR #41832: [Doc] Add ModernBertForSequenceClassification to scoring.md cross-en…

Description (problem / solution / changelog)

Purpose

[ModernBertForSequenceClassification is implemented in [vllm/model_executor/models/modernbert.py] with [SupportsCrossEncoding] and registered in [_SEQUENCE_CLASSIFICATION_MODELS] in [vllm/model_executor/models/registry.py], but it was missing from the supported cross-encoder models table in [docs/models/pooling_models/scoring.md.

This PR adds the missing row to the table.

Fix #41829

Test Plan

Documentation-only change, no code modification. Verified by cross-referencing:

  • [vllm/model_executor/models/registry.py] — [ModernBertForSequenceClassification] is in [_SEQUENCE_CLASSIFICATION_MODELS]
  • [vllm/model_executor/models/modernbert.py] — class implements [SupportsCrossEncoding]
  • [test_modernbert_reranker.py] — existing test uses Alibaba-NLP/gte-reranker-modernbert-base

AI assistance: This PR was created with the assistance of GitHub Copilot.

Co-authored-by: GitHub Copilot Signed-off-by: lzwgre [email protected]

Changed files

  • docs/models/pooling_models/scoring.md (modified, +1/-0)
RAW_BUFFERClick to expand / collapse

📚 The doc issue

Description The documentation page docs/models/pooling_models/scoring.md is missing ModernBertForSequenceClassification from the Text-only Cross-encoder Models table under Supported Models > Cross-encoder models.

Evidence [ModernBertForSequenceClassification] is a fully supported cross-encoder architecture in the vLLM codebase.

  1. Implemented in [vllm/model_executor/models/modernbert.py] with [SupportsCrossEncoding]: class ModernBertForSequenceClassification(nn.Module, SupportsCrossEncoding):
  2. Registered in [_SEQUENCE_CLASSIFICATION_MODELS] in [vllm/model_executor/models/registry.py]: "ModernBertForSequenceClassification": ( "modernbert", "ModernBertForSequenceClassification", ),
  3. Tested via [test_modernbert_reranker.py]with Alibaba-NLP/gte-reranker-modernbert-base.

Suggest a potential alternative/fix

Add the following row to the Text-only Models table in scoring.md, between [GteNewForSequenceClassification]and [LlamaBidirectionalForSequenceClassification](alphabetical order)。

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#database connection#vector store#embedding generation#cache error#pipeline error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

vllm - ✅(Solved) Fix [Doc]: scoring.md missing ModernBertForSequenceClassification from supported cross-encoder models [1 pull requests, 2 comments, 1 participants]