vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters (vllm-project vllm)
At a glance
- Source
- NVD
- EPSS
- EPSS 0.37 % · percentile 30 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Modified
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.
Weaknesses (CWE)
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | MEDIUM 6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | GitHub_M |
| CVSS 3.1 | MEDIUM 6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | NVD · security-advisories@github.com (Secondary) |
Advisories
- GHSA-83vm-p52w-f9pw — vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
- PYSEC-2026-145 — vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLL
European references
- ENISA EUVD · EUVD-2026-29800
- GCVE · GCVE-0-2026-44223
Affected configurations (NVD CPE)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*≥ 0.18.0 < 0.20.0
Affected products
| Product | Versions |
|---|---|
| vllm-project · vllm | affected >= 0.18.0, < 0.20.0 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |