8.7
High
CVE-2026-56340 vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing
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.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| vLLM 0.13 | earliest → < 0.13.0 | 0.13.0 |
| vLLM 0.10 | 0.10.2 → < 0.13.0 | 0.13.0 |
| Red Hat AI Inference Server | Versions not published | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Versions not published | |
| Red Hat OpenShift AI (RHOAI) | Versions not published |
References
- GHSA Advisory GHSA-mcmc-2m55-j8jj github.com
- VulnCheck Advisory: vLLM - Denial of Service via Unvalidated Multimodal Embeddings www.vulncheck.com
Timeline
- Published
- Last modified