CVE-2025-62164
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.
How to fix
- vllm vllm0.11.1 or later
- vllm0.11.1 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm vllm | 0.10.2 ≤ v < 0.11.1, 0.11.1 | 0.11.1 |
| vllmPyPI | 0.10.2 ≤ v < 0.11.1 | 0.11.1 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.