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.
References
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/pull/38610 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw | Mitigation Vendor Advisory |
| https://github.com/vllm-project/vllm/pull/38610 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw | Mitigation Vendor Advisory |
Configurations
History
15 May 2026, 15:16
| Type | Values Removed | Values Added |
|---|---|---|
| References | () https://github.com/vllm-project/vllm/pull/38610 - Issue Tracking, Patch | |
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw - Mitigation, Vendor Advisory |
14 May 2026, 15:37
| Type | Values Removed | Values Added |
|---|---|---|
| References | () https://github.com/vllm-project/vllm/pull/38610 - Issue Tracking, Patch | |
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw - Mitigation, Vendor Advisory | |
| First Time |
Vllm vllm
Vllm |
|
| CPE | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* |
12 May 2026, 20:16
| Type | Values Removed | Values Added |
|---|---|---|
| New CVE |
Information
Published : 2026-05-12 20:16
Updated : 2026-05-15 15:16
NVD link : CVE-2026-44223
Mitre link : CVE-2026-44223
CVE.ORG link : CVE-2026-44223
JSON object : View
Products Affected
vllm
- vllm