CVE-2026-54234
HIGHDescription
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.
How to fix
TridentStack Control can deploy fixes like this automatically across your Windows, macOS, and Linux fleet. See how it works
Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Exploit Intelligence
Moderate risk: more likely to be exploited than 47% of all known CVEs.
References
Related Vulnerabilities
Other CWE-20 (Improper Input Validation) vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2024-3400 | Critical | 10.0 | 100% | KEV + Ransom | - |
| CVE-2021-45105 | Medium | 5.9 | 100% | - | Fix |
| CVE-2021-44228 | Critical | 10.0 | 100% | KEV + Ransom | Fix |
| CVE-2021-21985 | Critical | 9.8 | 100% | KEV + Ransom | Fix |
| CVE-2020-3452 | High | 7.5 | 100% | KEV | Fix |
| CVE-2018-7600 | Critical | 9.8 | 100% | KEV + Ransom | Fix |
Common questions
How do I fix CVE-2026-54234?
Published advisories record a fix for 2 affected products. The "How to fix" section on this page lists the fixed version and source advisory for each one, so apply the entry matching what you actually run.
Is CVE-2026-54234 being actively exploited?
Not that we know of. CVE-2026-54234 is not in the CISA Known Exploited Vulnerabilities catalog. Its EPSS score of 0.62% is the estimated probability that it will be exploited in the next 30 days. That is higher than 47% of all scored CVEs.
How severe is CVE-2026-54234?
CVE-2026-54234 has a CVSS v3 base score of 7.5, rated high. CVSS rates the technical impact if the vulnerability is exploited, not how likely that is, so weigh it alongside the exploit-prediction score when you decide what to patch first.
What does CVE-2026-54234 affect?
Published advisories record a fix for registry.redhat.io/rhaiis/vllm (Red Hat / RHEL), registry.redhat.io/rhaiis/vllm (Rocky). Only products with a sourced advisory are listed, so treat this as what we can cite rather than a complete inventory.
Embed a live status badge for CVE-2026-54234
Markdown
[](https://tridentstack.com/cve/CVE-2026-54234)HTML
<a href="https://tridentstack.com/cve/CVE-2026-54234"><img src="https://tridentstack.com/cve/badge/CVE-2026-54234.svg" alt="CVE-2026-54234"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-07-07.