vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.
Fix
Patch, vendor advisory and mitigation references on NVD 2
- https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 6.5 · vllmNVD modified 2026-10-19 13:10
Affected (CPE criteria) 3
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*
References 5
- https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610 Product
- https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814 Product
- https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b Patch
- https://github.com/vllm-project/vllm/pull/27205 Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p Vendor Advisory