Skip to main content
CRITICAL

CVE-2025-47277

CVSS v3

9.8

CRITICAL

EPSS Score

1.0 %

exploit probability, as of 2026-10-12

CISA KEV

No

known exploited

Exploitation

—

SSVC status

Get an alert for each new CVE published for vllm. Watch vllm in CVE Watch Free account · no credit card

Affected and fixed versions

Packages from OSV.dev and products from the vendors' CSAF advisories.

version not verifiedVersions not verified: read as OSV.dev and the vendors publish them, not checked against each vendor's release list.

Packages

  • vllmPyPIfrom 0.6.5 · fixed in 0.8.5

Vendor advisories

  • CVE-2025-47277 Red Hat Product Security15 products fixed

    vllm: vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

  • RHSA-2025:15867 Red Hat Product Security1 product fixed

    Red Hat Security Advisory: Red Hat Enterprise Linux AI 1.5 (Intel Gaudi)

  • RHSA-2025:15843 Red Hat Product Security1 product fixed

    Red Hat Security Advisory: Red Hat Enterprise Linux AI 1.5 (AMD)

  • RHSA-2025:15841 Red Hat Product Security2 products fixed

    Red Hat Security Advisory: Red Hat Enterprise Linux AI 1.5 (NVIDIA)

  • RHSA-2025:15842 Red Hat Product Security1 product fixed

    Red Hat Security Advisory: Red Hat Enterprise Linux AI 1.5 (NVIDIA)

  • RHSA-2025:15838 Red Hat Product Security1 product fixed

    Red Hat Security Advisory: Red Hat Enterprise Linux AI 1.5 (NVIDIA)

7 more advisories

Full record on NVD

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.

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Published
2025-05-20
Last Modified
2025-08-13

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.

Is CVE-2025-47277 actively exploited?

Active exploitation of CVE-2025-47277 has not been confirmed. Its EPSS score was 1.0% on 2026-10-12, the estimated probability of exploitation in the next 30 days.

What is the CVSS score for CVE-2025-47277?

CVE-2025-47277 has a CVSS v3 base score of 9.8 (CRITICAL severity), with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

Running vllm? Hear about its next vulnerability

CVE Watch matches each new CVE to the vendors and products you list (vendor and product, not the version) and puts it in your alerts with its KEV and EPSS status.

Already have an account? Open CVE Watch

No credit card required · 50 free checks/month · Free API key