# CVE-2026-78684: vLLM DeepStream backend classification and pixel-limit enforcement bypass

Source: https://junglewise.ai/threats/cve-2026-78684-vllm-deepstream-backend-classification-and-pixel-limit  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-25. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-78684 · Severity: medium · CVSS 5.3 · Published 2026-08-25

vLLM is an open-source inference engine for large language models that supports video input processing. Attackers can exploit a flaw in how the DeepStream GPU video decoder is classified to bypass resource controls and trigger a partial denial of service affecting concurrent requests. By requesting GPU-accelerated video decoding that was not pre-configured at startup, an unauthenticated attacker can cause legitimate requests to time out and fail.

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-2026-78684 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-78684 being exploited in the wild.

**How severe is CVE-2026-78684?** Medium severity, with a CVSS score of 5.3, published 25 August 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.27.0; Vllm before 0.27.0.

**Is there a fix for CVE-2026-78684?** Yes. vllm (PyPI): upgrade to 0.27.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-78684 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-78684?** 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 0.27.0 or later

  ```sh
  pip install "vllm>=0.27.0"
  ```


## Technical details

The vulnerability stems from three root causes: (1) DeepStream is registered as an inner codec of OpenCV rather than as a standalone GPU backend, allowing backend_requires_gpu() to return False and requests to bypass GPU backend validation in VideoMediaIO.merge_kwargs(); (2) the DeepStream decode path calls probe_metadata() but omits the _check_frame_pixel_limit() validation check applied by other backends (OpenCV, PyAV, TorchCodec, PyNvVideoCodec), allowing oversized frames to be processed; and (3) DeepStream uses a process-wide singleton decode pool initialized on first request with user-controlled pool size, rather than at startup. An unauthenticated client can send a video inference request specifying backend="deepstream" to initialize the GPU decode pool and submit video that would be rejected by other backends, exhausting GPU resources and causing timeouts for concurrent requests. The fix requires registering DeepStream as a GPU-classified codec, enforcing pixel-limit checks, and making pool initialization startup-only.

## Affected products

- vLLM vLLM before 0.27.0

## Identifiers

- CVE-2026-78684
- PYSEC-2026-4003

## Timeline

- 2026-08-25: disclosed
- 2026-08-11: patched: fix available in version 0.27.0 and later

## References

- [https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba15a419](https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba15a419)
- [https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq](https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq)

## 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)