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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | < 0.27.0 | — |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | vllm | < 0.27.0 | 0.27.0 | GHSA-7m6h-x95x-82q5 |
Advisories 2
- WID-SEC-2026-2842 vllm: Mehrere Schwachstellen BSI CERT-Bund (WID) · Nov 9, 2026
- WID-SEC-2026-2739 vllm: Mehrere Schwachstellen BSI CERT-Bund (WID) · Oct 29, 2026
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
- https://github.com/vllm-project/vllm/issues/42860
- https://github.com/vllm-project/vllm/pull/49660
- https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924
- https://github.com/vllm-project/vllm/releases/tag/v0.27.0