Vulnerability Description
vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.
CVSS Score
MEDIUM
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e430025
- https://github.com/vllm-project/vllm/issues/42860
- https://github.com/vllm-project/vllm/pull/49660
- https://github.com/vllm-project/vllm/releases/tag/v0.27.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
FAQ
What is CVE-2026-73558?
CVE-2026-73558 is a vulnerability with a CVSS score of 5.3 (MEDIUM). vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another b...
How severe is CVE-2026-73558?
CVE-2026-73558 has been rated MEDIUM with a CVSS base score of 5.3/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-73558?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.