CVE-2026-54234: vllm Input Validation Flaw

Description

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.

Is your site exposed to CVE-2026-54234?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

7.5

HIGH

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

EPSS — Exploit Prediction

0.0034

Probability of exploitation

0.27%

Percentile rank

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)

CWE-20 Improper Input Validation

CWE-1284 CWE-1284

Affected Products

Vendor	Product	Versions
vllm	vllm	< 0.24.0

References

Advisories & Patches

https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca https://github.com/vllm-project/vllm/pull/44744 https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f

Exploits

https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f

Frequently Asked Questions

What is CVE-2026-54234? +

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0. It has a CVSS v3.1 base score of 7.5 (HIGH).

How severe is CVE-2026-54234? +

CVE-2026-54234 has a CVSS v3.1 score of 7.5 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0034, placing it in the 0th percentile for exploitation probability.

What products are affected by CVE-2026-54234? +

CVE-2026-54234 affects products from vllm, specifically: vllm. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2026-54234? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-13826

Zervit's portable HTTP/web server is vulnerable to remote DoS attacks when a configuration reset request is made. The vulnerability is …

CVE-2024-54011

Penetration Testing engineers at Amazon have discovered a flaw where the camera system fails to properly handle data supplied in …

CVE-2026-62656

A security flaw was found in certain NETGEAR RAX models that could allow a logged-in user to send specially crafted …

CVE-2026-62658

A security flaw was discovered in certain NETGEAR Nighthawk RAX series routers that could allow someone already logged in to …

CVE-2026-56349

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail …

CVE-2026-6409

A Denial of Service (DoS) vulnerability exists in the Protobuf PHP library during the parsing of untrusted input. Maliciously structured …

CVE-2026-54234