CVE-2026-54234
vllm-project vllm 취약점
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 triggerin...
- 대응 우선순위
- 점검
- CVSS
- 7.5
- EPSS
- 0.36% 백분위 28.9% · 2026.07.28 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.07.07