p PatchFirst

CVE-2026-100653

CVE-2026-100653 · vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation

Cette page présente des faits issus de sources publiques. Consultez l’avis original avant toute mise à jour.

vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/funaudiochat.py and the Qwen2VLConfig.from_pretrained call used by Tarsier2ProcessingInfo in vllm/model_executor/models/qwen2_vl.py. As a result, deployments pinned to a reviewed revision still resolve these behavior-affecting processor, tokenizer, and config artifacts from the repository's default revision, so a later change to the upstream default branch can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration without any change to the operator's configured pin. This is a supply-chain integrity and reproducibility failure for pinned deployments; it is residual to the earlier fix tracked as GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 and does not constitute remote code execution or a trust_remote_code=False bypass. The issue is fixed in version 0.28.0.

CVSS 8.3 · Élevée · EPSS 0,3% · Correctif disponible

Publication
Mise à jour

Pile logicielle: python

Produits et versions concernés

  • vllm

    Versions du logiciel
    • ≥ 0.22.1, < 0.28.0: Concernée (semver)
    • 0.28.0: Non concernée (semver)

    Mettez à jour vers 0.28.0

  • vllm PyPI

    Versions du logiciel
    • 0.22.1
    • 0.23.0
    • 0.24.0
    • 0.25.0
    • 0.25.1
    • 0.26.0
    • 0.27.0
    • 0.27.1
    Plages de versions concernées
    • ECOSYSTEM: ≥ 0.22.1, < 0.28.0

    Mettez à jour vers 0.28.0

Sources originales

Vérifiez votre serveur →