vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
High Security Advisories for vllm in pypi Clear Filters
High
4 days ago
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
pypi
vllm
High
about 2 months ago
vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class
pypi
vllm
High
3 months ago
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
pypi
vllm
High
7 months ago
Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration
pypi
vllm
High
10 months ago
vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
pypi
vllm