CVE-2025-47277: 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 us...

Description

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.

Metrics

CVSS 3.1

9.8/10

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS Probability

0.93%

56.0th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

CWE-502

Affected Software

Vendor	Product	Versions
Vllm	Vllm	>= 0.6.5, < 0.8.5

References

https://docs.vllm.ai/en/latest/deployment/security.htmlTechnical Description
https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7Patch
https://github.com/vllm-project/vllm/pull/15988Issue Tracking, Patch
https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fvExploit, Vendor Advisory

Timeline

Published: May 20, 2025
Last Modified: Jun 17, 2026
Status: Analyzed

Frequently Asked Questions

What is CVE-2025-47277?

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.

How severe is CVE-2025-47277?

CVE-2025-47277 has a CVSS score of 9.8/10 (CRITICAL severity). The EPSS model estimates a 0.93% probability of exploitation in the next 30 days.

How do I fix CVE-2025-47277?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2025

View all 2025CVEs →