8.8High

CVE-2026-56340vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM vLLM; Red Hat Red Hat AI Inference Server; Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3; Red Hat Red Hat OpenShift AI (RHOAI) Published: (5 months ago)

Description

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

Weakness (CWE): CWE-20CWE-787

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
Red Hat Red Hat AI Inference Server all versions
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 —
Red Hat Red Hat OpenShift AI (RHOAI) —
vLLM vLLM 0.10.2 – < 0.13.0, fixed 0.13.0

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.10.2 < 0.13.0