CVE-2026-44223
vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
Using vllm by vllm-project?
Get instant alerts when new vulnerabilities affect vllm - before attackers find them.
Description
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 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.
Remediation
No guide yetNo remediation guidance has been written for this CVE yet. What the record does show:
References (2)
SSVC — Action Prioritization
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
CVSS
- Attack Vector
- NETWORK
- Complexity
- LOW
- Privileges
- LOW
- User Interaction
- NONE
- Scope
- UNCHANGED
- Confidentiality
- NONE
- Integrity
- NONE
- Availability
- HIGH
Quick Info
Get alerted
Stop reading CVE feeds looking for your own stack
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.