CVE-2026-56340

published 20 Jun 2026 · updated 8 Nov 2026

vLLM - Denial of Service via Unvalidated Multimodal Embeddings

8.8HighCVSS 8.8EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. Fixed in 0.13.0.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
vLLM>=0.10.2 <0.13.00.13.0

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-56340 severity on Zeptric[![CVE-2026-56340](https://zeptric.io/badge/cve/CVE-2026-56340.svg)](https://zeptric.io/cve/CVE-2026-56340)