CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

CVE-2026-115912

In versions prior to 0.32.0 , the vLLM inference and serving engine for large language models is vulnerable to arbitrary Python execution. An authenticated caller can exploit this by placing forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-o...