Description
vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing logprob_token_ids limits in the Rust gRPC frontend. Attackers can send Generate or GenerateStream requests with output_logprobs enabled and more than 128 output_candidates.token_ids, triggering a fatal sampler exception that crashes the engine.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | 0.22.0 – < 0.24.0 | 0.24.0 |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | vllm | >= 0.22.0, < 0.24.0 | 0.24.0 | PYSEC-2026-4350 |
Advisories 1
- WID-SEC-2026-3828 vllm: Mehrere Schwachstellen BSI CERT-Bund (WID) · Nov 12, 2026
References
- GitHub Security Advisory (GHSA-6pgw-f3pv-4h8q) vendor-advisory
- VulnCheck Advisory: vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_ids third-party-advisory