CVE-2026-105754

MEDIUM
Published Oct 5, 2026 Modified Oct 8, 2026 CWE-20 CWE-617 CWE-639 CWE-668 CWE-704 CWE-1284

Description

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

Is your site exposed to CVE-2026-105754?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

6.5
MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS — Exploit Prediction

0.0027
Probability of exploitation
0.18%
Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-20 Improper Input Validation
CWE-617 CWE-617
CWE-639 CWE-639
CWE-668 CWE-668
CWE-704 CWE-704
CWE-1284 CWE-1284

Affected Products

Vendor Product
vllm vllm

References

Frequently Asked Questions

What is CVE-2026-105754? +
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0. It has a CVSS v3.1 base score of 6.5 (MEDIUM).
How severe is CVE-2026-105754? +
CVE-2026-105754 has a CVSS v3.1 score of 6.5 out of 10, rated MEDIUM. This is a medium-severity vulnerability that should be remediated as part of regular maintenance. The EPSS score is 0.0027, placing it in the 0th percentile for exploitation probability.
What products are affected by CVE-2026-105754? +
CVE-2026-105754 affects products from vllm, specifically: vllm. Check the affected products table above for specific version ranges.
How do I check if I'm vulnerable to CVE-2026-105754? +
You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

Don't wait for an exploit

Scan your website for vulnerabilities like CVE-2026-105754 — free, no signup required.