vLLM denial of service via prompt embeds on M-RoPE models
vllm-project vllm
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| vllm PyPI |
|
|
Original description
vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.
From the CVE record · GitHub_M