CVE-2026-54234
vLLM is a high-throughput and memory-efficient inference and …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca
- github.com/vllm-project/vllm/pull/44744
- github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f
- nvd.nist.gov/vuln/detail/CVE-2026-54234
- github.com/advisories/GHSA-8wr5-jm2h-8r4f
- nvd.nist.gov/vuln/detail/CVE-2026-54234
- cve.org/CVERecord?id=CVE-2026-54234
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.