5.9Medium
CVE-2026-126398vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models
Description
vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients.
Weakness (CWE):
CWE-617
Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.
Affected products and versions
| Vendor | Product | Versions | |
|---|---|---|---|
| vllm-project | vllm | 0.28.0 – < 0.30.0, fixed 0.30.0 |
References and patches
- GitHub Security Advisory (GHSA-5q78-j82c-2vr2) vendor-advisory
- VulnCheck Advisory: vLLM 0.28.0 before 0.30.0 Denial of Service via Prompt Embeds on XD-RoPE Models third-party-advisory