# CVE-2026-44223: vLLM denial of service in extract_hidden_states speculative decoding

Source: https://junglewise.ai/threats/cve-2026-44223-vllm-denial-of-service-in-extract-hidden-states-speculative  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-05-12. Updated: 2026-06-22  
License: CC BY 4.0 with a link back

CVE-2026-44223 · Severity: medium · CVSS 6.5 · Published 2026-05-12

vLLM is an open-source engine used to serve Large Language Models (LLMs) for AI applications. A flaw in its speculative decoding feature allows a user to crash the entire server process by sending a single request containing specific parameters, such as a repetition penalty. This results in a complete denial of service, making the AI application unavailable to all users until the process is manually restarted.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2026-44223 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-44223 being exploited in the wild.

**How severe is CVE-2026-44223?** Medium severity, with a CVSS score of 6.5, published 12 May 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0.18.0,fixed=0.20.0.

**Is there a fix for CVE-2026-44223?** Yes. vllm (PyPI): upgrade to 0.20.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-44223 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-44223?** Check whether you run vllm (PyPI) or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.20.0 or later

  ```sh
  pip install "vllm>=0.20.0"
  ```


## Technical details

A denial-of-service vulnerability exists in vLLM's 'extract_hidden_states' speculative decoding proposer due to an incorrect tensor shape calculation. Following a refactor in version 0.18.0, the 'propose()' method fails to account for semantic changes in 'sampled_token_ids' after the first decode step, returning a tensor of shape (batch_size, 2) instead of the expected (batch_size, 1). When a request includes sampling penalty parameters (repetition, frequency, or presence penalties), this shape mismatch triggers a broadcast error and a RuntimeError, crashing the EngineCore process. The attack can be executed by any authenticated user capable of sending inference requests with custom sampling parameters. The issue is resolved in version 0.20.0 by ensuring the return value is correctly sliced.

## Affected products

- vLLM Project vLLM >= 0.18.0, < 0.20.0

## Identifiers

- CVE-2026-44223
- GHSA-83vm-p52w-f9pw
- PYSEC-2026-145

## Timeline

- 2026-03-31: other: Fix pull request submitted
- 2026-04-09: patched: Fix merged into main branch
- 2026-04-28: advisory: Vendor advisory published via GitHub
- 2026-05-12: disclosed: CVE published to NVD

## References

- [https://github.com/vllm-project/vllm/pull/38610](https://github.com/vllm-project/vllm/pull/38610)
- [https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw](https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)