CVE-2026-93840
LOWDescription
vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
Is your site exposed to CVE-2026-93840?
Run a free security scan — no signup, results in seconds.
CVSS v3.1 Score
EPSS — Exploit Prediction
EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.
Weakness Type (CWE)
References
Other References
Frequently Asked Questions
What is CVE-2026-93840? +
How severe is CVE-2026-93840? +
How do I check if I'm vulnerable to CVE-2026-93840? +
Related Vulnerabilities
A weakness in Automated Logic and Carrier i-Vu Gen5 router on driver version drv_gen5_106-01-2380, allows malformed packets to be sent …
Taiko Alethia is an Ethereum-equivalent, permissionless, based rollup designed to scale Ethereum without compromising its fundamental properties. In 2.3.1 and …
Improper validation in Power Management Firmware (PMFW) may allow an attacker with privileges to pass malformed workload arguments when exporting …
A stack-based buffer overflow vulnerability in the WatchGuard Fireware OS iked process allows a remote unauthenticated attacker to execute arbitrary …
Integer Overflow, Improper Validation of Array Index, Uncontrolled Recursion and Memory Allocation with Excessive Size Value in the Go implementation …
Improper validation of array index vulnerability in Velneo vServer. This issue affects vServer: from 36.0 before 36.6 and from 37.0 …