vulnti.work

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…

Medium CVSS 6.5
CVECVE-2026-100653
First seen2026-09-26 16:31 UTC
Disclosed2026-09-26 14:16 UTC
Last updated2026-09-26 16:31 UTC
Channel statusauto

Summary

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_e…

In-depth triage

No in-depth report has been generated yet (DR-003 v2 AI pipeline is under construction).

Sources

  • NVD DATABASE

Original Links

Timeline

  1. nvd_ingest NVD