CVE-2025-62164
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.89%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
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.
- CVSS 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.89% probability · 57th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-20, CWE-123, CWE-502, CWE-787
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
- https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84bPatch
- https://github.com/vllm-project/vllm/pull/27204Issue Tracking, Patch, Vendor Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-mrw7-hf4f-83pfIssue Tracking, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.