vLLM denial of service via prompt embeds on M-RoPE models

Summary Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server. Sending a pure prompt embeds payload in a /v1/completions request with a model usi...

CVE-2026-55514

A flaw was found in vLLM, a library for Large Language Model LLM inference and serving. A remote attacker, authorized to make a /v1/completions request, can send a specially crafted prompt embeds payload. This action causes the EngineCore to fail an assertion and fatally crash, leading to a Denia...

CVE-2026-44223

vLLM contains a vulnerability (CVE-2026-44223) where the extract_hidden_states speculative decoding pathway can crash the EngineCore process if any request uses penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). The issue arises from an incorrect tensor shape after t...

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.20.0 contained a security vulnerability. This vulnerability stemmed from the extracthiddenstates speculative decoding proposal, which returned tensor...

PT-2026-38288

Name of the Vulnerable Software and Affected Versions vLLM versions 0.18.0 through 0.19.1 Description The extract hidden states speculative decoding proposer returns a tensor with an incorrect shape after the first decode step, leading to a RuntimeError that crashes the EngineCore process. This...