Skip to content
fr Sign in
6.5 Medium

CVE-2026-44223 vLLM is an inference and serving engine for large language models (LLMs)

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.

Affected products and versions

Product Affected versions Fixed in
vllm 0.18 0.18.0 → < 0.20.0 0.20.0

References

Timeline

  1. Published
  2. Last modified

Other CVEs of vllm

The 121 CVEs of vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High
Track this CVE