Reachable assertion in vLLM - CVE-2026-126398
Published: November 9, 2026 / Updated: November 13, 2026
Vulnerability identifier: #VU162985
CSH Severity: Medium
CVSS v4: 8.2 [CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N]
CVE-ID: CVE-2026-126398
CWE-ID: CWE-617
Exploitation vector: Remote access
Exploit availability:
No public exploit available
Vulnerability details
The vulnerability allows an unauthenticated remote attacker to terminate the vLLM engine and API server, disconnecting all concurrent clients.
The vulnerability exists due to a reachable assertion in the V1 GPU model runner when an XD-RoPE model receives embeddings without token IDs. An unauthenticated remote attacker can send one embeddings-only request to /v1/completions when --enable-prompt-embeds is enabled and API authentication is disabled, causing service-wide denial of service.
Affected software
vLLM
How to mitigate CVE-2026-126398
Install security update from vendor's website.
vLLM - update to 0.30.0