Integer overflow in Vllm
CVE-2026-73558
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.
Vulnerability class: Integer Overflow
Published · last modified .
CVSS v3 metric
CVSS v3 base score 5.3 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N.
EPSS exploit prediction
EPSS 0.004, 36.2th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.27.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924 (Patch)
- https://github.com/vllm-project/vllm/issues/42860 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/pull/49660 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/releases/tag/v0.27.0 (Release Notes)
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5 (Exploit, Vendor Advisory)