CVE-2026-54234

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 convert...

Linux Distros Unpatched Vulnerability : CVE-2023-1428

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - There exists an vulnerability causing an abort to be called in gRPC. The following headers cause gRPC's C++ implementation to abort when called via http2: te: x...