HighVulnerabilityLLM-specific
CVE-2026-116180: vLLM denial of service through prompt_logprobs on cached prefixes
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-116180
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
Summary
vLLM from 0.8.5 before 0.31.0 contains a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, causing tokenizer decode to raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- MediumCVE-2026-116181: vLLM improper input validation of stop_token_ids crashes engineSimilar attack · NVD/CVE Database
- HighCVE-2026-116179: vLLM resource exhaustion through media_io_kwargs video frame-count overrideSimilar attack · NVD/CVE Database
- MediumCVE-2026-116178: vLLM denial of service via inconsistent multimodal metadataSimilar attack · NVD/CVE Database
- HighCVE-2026-116177: vLLM uncontrolled resource consumption via image decompression bombSimilar attack · NVD/CVE Database
- MediumCVE-2026-116175: vLLM decompression bomb in AudioMediaIO via /v1/chat/completions audio inputSimilar attack · NVD/CVE Database