← Vulnerability feed

Vulnerability record · CVE-2026-54234 · published 6 July 2026

CVE-2026-54234: Vllm improper input validation vulnerability

Vllm · Vllm

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.

7.5 CVSS 3.1 High EPSS 0.62% · top 52.6% CWE-20 · Improper input validationCWE-1284 · CWE-1284
7.5CVSS 3.1 base score
0.62%EPSS exploitation probability, 30 days
NoNot in CISA KEV
1Affected product versions listed by NVD
4References, 2 tagged exploit
7 Jul 2026Last modified by NVD

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

Affected products

1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.

References

LinkTags
https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca Patch
https://github.com/vllm-project/vllm/pull/44744 Issue TrackingPatch
https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f Vendor AdvisoryExploit
https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f Vendor AdvisoryExploit

Track CVE-2026-54234 inside VULONE

Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.

Start free Open in platform

Related vulnerabilities

Same products first, then exploited flaws of the same weakness class.

9.8CVE-2026-25960Vllm server-side request forgery (ssrf) vulnerabilityvLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in…EPSS 0.72%9.8CVE-2026-22778Vllm sensitive information in log file vulnerabilityvLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multim…EPSS 3.8%9.8CVE-2026-22807Vllm code injection vulnerabilityvLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging …EPSS 0.83%9.8CVE-2025-47277Vllm deserialization of untrusted data vulnerabilityvLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments u…EPSS 0.96%9.8CVE-2025-32444Vllm deserialization of untrusted data vulnerabilityvLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM in…EPSS 1.8%9.8CVE-2024-11041Vllm deserialization of untrusted data vulnerabilityvllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse receive…EPSS 1.6%9.1CVE-2026-48746Vllm http request smuggling vulnerabilityvLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette'…EPSS 1.2%9.0CVE-2025-29783Vllm deserialization of untrusted data vulnerabilityvLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization…EPSS 0.73%

Source: NIST National Vulnerability Database (record CVE-2026-54234), CISA KEV, FIRST EPSS (scores of 2026-09-26). This page is refreshed as NVD updates the record.