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.

CVSS 3.1

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

EPSS

0.3% chance of exploitation in the next 30 days; higher than 18% of CVEs (scores of 2026-10-25)

CWEs

CWE-20, CWE-617, CWE-639, CWE-668, CWE-704, CWE-1284

Published

2026-10-05

Modified

2026-10-08

Record from

the NVD, synced 2026-10-19

Affected

• vllm:vllm

Packages (OSV)

References

• https://github.com/vllm-project/vllm/commit/1970f3ed4be7fa8620e4ddc4a12c36a8384cfc27
• https://github.com/vllm-project/vllm/pull/51898
• https://github.com/vllm-project/vllm/releases/tag/v0.30.0
• https://github.com/vllm-project/vllm/security/advisories/GHSA-ph72-cqr5-qpp7

Check your stackJSON