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.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-617"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/126xxx/CVE-2026-126398.json"
}