vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Moderate Security Advisories for vllm in pypi Clear Filters
Moderate
about 1 month ago
vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server
pypi
vllm
Moderate
6 months ago
vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
pypi
vllm
Moderate
6 months ago
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
pypi
vllm
Moderate
7 months ago
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
pypi
vllm