PT-2026-55999 · Vllm · Vllm

Qthequartermasterman · Published 2026-07-06 · Updated 2026-07-06 · CVE-2026-55514

NVD

CVSS v4.0

7.1

High

Base vector

AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

Fix

Assertion Failure

Weakness Enumeration

CWE-617

Related Identifiers

CVE-2026-55514

Affected Products

Vllm

References · 5

• https://nvd.nist.gov/vuln/detail/CVE-2026-55514 · Security Note
• https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g · Note
• https://github.com/vllm-project/vllm/pull/45252 · Note
• https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65 · Note
• https://github.com/vllm-project/vllm/releases/tag/v0.24.0 · Note