Skip to content

CVE-2026-54234

Vllm vulnerability

7.5 HIGHPublic exploitEPSS 0.62%
  1. Published6 Jul 2026

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.

CVSS 3.1 breakdown

Attack vectorNetwork
Attack complexityLow
Privileges requiredNone
User interactionNone
ScopeUnchanged
ConfidentialityNone
IntegrityNone
AvailabilityHigh
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected products

Vllm< 0.24.0

Frequently asked

Is CVE-2026-54234 being actively exploited?

CVE-2026-54234 is not in the CISA KEV catalog. A public exploit reference exists, so treat it as exploitable. Its EPSS exploit probability is 0.62%.

How severe is CVE-2026-54234?

CVE-2026-54234 has a CVSS 3.1 base score of 7.5, rated high. EPSS estimates a 0.62% probability of exploitation.

Which products are affected by CVE-2026-54234?

Affected products include Vllm.

How do I fix CVE-2026-54234?

Upgrade affected software to a fixed version, for example Vllm 0.24.0 or later, then confirm no affected versions remain in your inventory.

How Secuno handles this

Secuno correlates vulnerabilities like CVE-2026-54234 against the real software inventory on every managed device, every day. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.

Get Patch this first every Monday

Five vulnerabilities that matter this week, ranked on real exploitation. Plain language, one email, no spam.

You can unsubscribe with one click from every issue. We handle your details as described in our privacy policy.

Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.