- CVSS
- MEDIUM · 5.3v3.1CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
- Published
- 2026-08-13
- Weakness
- CWE-190
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-73558
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.
References
- https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924
- 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
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-73558 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.