CVE-2026-100653
vLLM is an inference and serving engine for large language models
- Risk score
- 48/100
- CVSS
- 6.5 v3.1
- Exploit chance (30 days)
- 0.3%
- Published
- 26 Sep 2026
Open in the live forecast Today's forecast
What to know
- What it is
- 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 sp…
- Affected
- Vllm before 0.28.0
- Fix
- Upgrade Vllm to 0.28.0 or later.
- Exploitation
- Public proof of concept
Story map
At a glance
Vllm: Amber, patch this week. vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA ten…
The flaws
- CVE-2026-100653: VLLM is an inference and serving engine for large language models (CVSS 6.5 · EPSS 0%)
- CVE-2026-100652: Improper input validation (CVSS 7.5 · EPSS 0%)
- CVE-2026-105759: VLLM is an inference and serving engine for large language models (CVSS 7.5 · EPSS 0%)
- CVE-2026-103241: Denial of service (CVSS 7.5 · EPSS 1%)
The fix
Upgrade Vllm: 0.28.0 · 0.30.0 or later on your release line
Who is exposed: Vllm
Where it stands
- Public proof of concept
Connects to
- Same weakness: CWE-348 (CWE-348). 10 other warnings in 30 days
- Same product: Earlier Vllm warnings. 15 in the last 90 days
Why it is Yellow
- CVSS 6.5 medium
- Public exploit or proof of concept referenced
References
- https://github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628q
- https://www.vulncheck.com/advisories/vllm-0.22.1-before-0.28.0-incomplete-artifact-pin-propagation
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628q
Original description
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.
Last activity 26 Sep 2026. Patch Forecast updates every hour.