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.

Weaknesses 4

Affected Products 3

References 3

• github.com https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
  Patch
• github.com https://github.com/vllm-project/vllm/pull/27204
  Issue TrackingPatchVendor Advisory
• github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-mrw7-hf4f-83pf
  Issue TrackingVendor Advisory

Remediation

• github.com https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b
  Patch
• github.com https://github.com/vllm-project/vllm/pull/27204
  Issue TrackingPatchVendor Advisory