High 7.5Published Jul 6, 2026

CVE-2026-54234vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.

Updated under an hour ago (2026-10-19 08:30 UTC)

Does this affect you?

It affects vllm. Add what you run to find out whether that includes you.

No exploitation reported and no EPSS estimate yet.

Do this next

Start free and add your stack

Free account, 1 product

Every CVE for vllm

Exploited in the last 30 days

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: 7.5 HIGH (v3.1, NVD)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Weakness (CWE): CWE-20, CWE-1284
Known exploited: Not in CISA's KEV catalog
EPSS (exploitation in the next 30 days): Not loaded for this CVE
Assigned by: Not given
NVD analysis: Analyzed
Record last updated: Jul 7, 2026
First seen by InfoSec Signals: Oct 9, 2026

Affected products

Affected products

vllm vllm vllm:vllm	before 0.24.0	NVD

References

https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26capatch
https://github.com/vllm-project/vllm/pull/44744issue-tracking, patch
https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4fvendor-advisory, exploit

The CVE record on cve.org NVD's entry

The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.