PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-54234 vllm-project CVE debrief

A high-throughput and memory-efficient inference and serving engine for LLMs, vLLM, is vulnerable to a denial of service attack. Prior to version 0.24.0, a specific multi-request speculative decoding workload can cause the engine to crash, resulting in a service-wide denial of service for other clients until the worker is restarted. The vulnerability exists in the vLLM engine's handling of speculative decoding workloads, and a remote client can send a specific sequence of requests to the engine, causing it to crash.

Vendor
vllm-project
Product
vllm
CVSS
HIGH 7.5
CISA KEV
Not listed in stored evidence
Original CVE published
2026-07-06
Original CVE updated
2026-07-07
Advisory published
2026-07-06
Advisory updated
2026-07-07

Who should care

Users of vLLM versions prior to 0.24.0 should be aware of this vulnerability and take steps to mitigate it. This includes updating to version 0.24.0 or later and implementing compensating controls to detect and prevent similar attacks. Operators, platform administrators, vulnerability management teams, and security teams should review the vulnerability's impact and take necessary actions.

Technical summary

The vulnerability exists in the vLLM engine's handling of speculative decoding workloads. A remote client can send a specific sequence of requests to the engine, causing it to crash and resulting in a denial of service for other clients. The issue is fixed in version 0.24.0. The engine's embedding and attention path crash when consuming the out-of-vocabulary value produced by the rejection sampler.

Defensive priority

High

Recommended defensive actions

  • Update vLLM to version 0.24.0 or later
  • Implement compensating controls to detect and prevent similar attacks
  • Monitor the engine for suspicious activity
  • Restrict access to the engine to authorized clients only
  • Review the supplied official advisory or CVE record to validate affected scope, severity, and vendor guidance
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record was published on 2026-07-06T21:16:56.477Z and has been modified since then. The NVD entry is currently Analyzed. The vulnerability has a CVSS score of 7.5 and a severity of HIGH. Evidence is limited, and defenders should verify the vulnerability's impact and affected scope. The rejection sampler can 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.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-54234 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-54234

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-54234 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-54234

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.