Advisoriesby IbisvLLMPYSEC-2026-4350
vLLM: denial of service
Fix: upgrade to 0.24.0 or later
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 versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | >= 0.22.0, < 0.24.0 | 0.24.0 |
Details and references
- CVSS 3.1
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Severity from
- the CVSS score
- Also known as
- CVE-2026-116173, GHSA-6pgw-f3pv-4h8q
More vLLM advisories
All vLLM
vllm p2p never connected zmq_exhaustionCVE-2026-94624fixed in 0.32.0vLLM: server-side request forgeryCVE-2026-116176fixed in 0.24.0vLLM: resource exhaustionCVE-2026-116177fixed in 0.25.0vLLM: denial of serviceCVE-2026-116178fixed in 0.30.0vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)CVE-2026-114055fixed in 0.31.0vLLM: insufficient authenticity checkCVE-2026-114050fixed in 0.31.0