CVE-2026-54234
CVE-2026-54234 · vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection
Здесь приведены факты из открытых источников об уязвимостях. Перед обновлением ознакомьтесь с исходным сообщением.
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 · Высокий · EPSS 0,6% · Есть исправление
- Опубликовано
- Обновлено
Стек: python