INCIDENT MAP

Browse / Unbounded Consumption / CVE-2026-114055

vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)

CVE-2026-114055 ยท 2026-10-23 high

Class
Unbounded Consumption (filed by a model that read the advisory)
Technique
Denial of service
Affected
vllm (PyPI)
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS
0.4% chance of exploitation in 30 days

How it works, in short

Clients can set per-request processor arguments such as image size that are passed unchecked to processors, forcing huge allocations that exhaust server memory. (Our summary, written by a model. The source text is below.)

Details

Summary

API clients can supply arbitrary mm_processor_kwargs per request. vLLM
forwards these values through the multimodal rendering and processing pipeline
to Hugging Face and custom image/video processor constructors and calls.
Resource-sensitive values such as image size, patch size, patch count, crop
count, or frame count can therefore be controlled by a remote client.

For processors that upscale inputs, a single request can force an allocation
large enough to terminate the API server or worker with an out-of-memory
condition.

Affected Components

The per-request field was introduced in commit
041e29471671a3d43afedb6a749421d56ef4d3e7 and first shipped in v0.7.3.
The generic forwarding path remains present in current main.

The Isaac path is a concrete high-amplification example:

Equivalent constructor forwarding exists in InternVL-derived processors,
H2OVL, Step3VL, NemotronVL, and other multimodal processors. The issue is at
the shared remote-input boundary and is not limited to a fixed model list.

Impact

Remediation

Reject non-empty per-request mm_processor_kwargs at every API-server request
schema by default. Operators serving only trusted clients can explicitly opt
in to the existing override behavior. Server-level --mm-processor-kwargs and
offline LLM overrides remain available.

This shared boundary covers current and future multimodal processors instead
of maintaining a model-specific list or a denylist that can miss custom
processor arguments.

A patch for this was merged here: https://github.com/vllm-project/vllm/pull/58830

References

Source: GitHub Advisory Database, used under CC BY 4.0.