Vulnerability · Published Oct 25, 2026 · Assigned by VulnCheck

CVE-2026-116173vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_ids

Medium 5.9

In plain English

A medium-severity improper input validation in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 27% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)5.9Medium

Exploit odds (30 days)0.3%top 72.5% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.24.0	PYSEC-2026-4350

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	0.22.0 – before 0.24.0

Weakness: CWE-20 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

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