6 matches found
Reachable Assertion
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via a reachable assert in GPUModelRunner.initxdropepositions that crashes the EngineCore and API server process when an...
8.2CVSS5.8AI score0.00367EPSS
SaveExploits0References2
20