CVE-2026-44223

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.

Weakness classification

• security-advisories@github.com: CWE-131

Primary references

• security-advisories@github.com — Issue Tracking, Patch
• security-advisories@github.com — Mitigation, Vendor Advisory
• 134c704f-9b21-4f2e-91b3-4a467353bcc0 — Issue Tracking, Patch
• 134c704f-9b21-4f2e-91b3-4a467353bcc0 — Mitigation, Vendor Advisory