VDB

CISA-2025-62164

CISA-2025-62164 PUBLISHED CVSS 8.8 HIGH

Reported by GitHub_M · Published November 21, 2025

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

Risk Scores

CVSS 3.1
8.8
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected Products

VendorProductVersions
vllm-projectvllm>= 0.10.2, < 0.11.1
vllm-projectvllm*, >= 0.10.2, < 0.11.1

Timeline

  • Nov 21, 2025 CVE Published
  • Nov 24, 2025 CVE Updated
Open in Interactive Console →
$ Console Community · 100/wk Open console ›