漏洞信息
# vLLM 通过 PyNcclPipe 通信服务允许远程代码执行
N/A
提示
尽管我们采用了先进的大模型技术,但其输出仍可能包含不准确或过时的信息。
神龙会尽力确保数据准确,但也请结合实际情况进行甄别与判断。
神龙祝您一切顺利!
漏洞标题
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
漏洞描述信息
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured.
CVSS信息
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
漏洞类别
可信数据的反序列化
漏洞标题
vLLM 代码问题漏洞
漏洞描述信息
vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.6.5至0.8.4版本存在代码问题漏洞,该漏洞源于PyNcclPipe KV缓存传输未正确限制TCPStore接口访问范围。
CVSS信息
N/A
漏洞类别
代码问题