CVE-2025-48944
vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference worker with a single request. The worker will remain down until it is restarted. Version 0.9.0 fixes the issue.
- Affected products
- Vllm
- Vllm
- < 0.9.0
- Fix
- Available
- CVSS 3.1
- 6.5 MEDIUM
- EPSS
- 0.4% (37th percentile)
- Weakness
- CWE-20
- NVD status
- Analyzed
- Published
- 2025-05-30
No indexed exploits for CVE-2025-48944 yet
Our index is partial: it proves presence, never absence
No exploit for CVE-2025-48944 has been indexed yet. Our index is built from live traffic and upstream syncs, so this page can only say what it knows — not that no exploit exists.