CVE-2026-34756: vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
(updated )
A Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue.
References
- access.redhat.com/errata/RHSA-2026:36005
- access.redhat.com/errata/RHSA-2026:36006
- access.redhat.com/security/cve/CVE-2026-34756
- bugzilla.redhat.com/show_bug.cgi?id=2455425
- github.com/advisories/GHSA-3mwp-wvh9-7528
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2298.yaml
- github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380
- github.com/vllm-project/vllm/pull/37952
- github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528
- nvd.nist.gov/vuln/detail/CVE-2026-34756
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34756.json
Code Behaviors & Features
Detect and mitigate CVE-2026-34756 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →