Vulnerability in Vllm
CVE-2026-100653
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N.
EPSS exploit prediction
EPSS: 0.003 (27.7th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 28th percentile — 27.7% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.003 · change: +0.001
Affected products
Weakness classification (CWE)
References
- GitHub Security Advisory (GHSA-hhv2-872h-628q) (vendor-advisory, Exploit, Mitigation, Vendor Advisory)
- Patch Commit (Patch, patch)
- VulnCheck Advisory: vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-100653?
- CVE-2026-100653 is a medium-severity vulnerability in Vllm, classified under CWE-348. CVSS score: 6.5/10. Published 2026-09-26.
- How severe is CVE-2026-100653?
- Medium severity. CVSS v3 base score is 6.5 out of 10.