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.
Project Subscriptions
No data.
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Thu, 13 Aug 2026 18:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vllm-project
Vllm-project vllm |
|
| Vendors & Products |
Vllm-project
Vllm-project vllm |
Thu, 13 Aug 2026 15:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | vLLM: Cross-User Data Leak Vulnerability | |
| Weaknesses | CWE-190 | |
| References |
|
|
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-08-13T15:38:40.181Z
Reserved: 2026-08-12T20:53:46.380Z
Link: CVE-2026-73558
No data.
Status : Received
Published: 2026-08-13T15:20:18.220
Modified: 2026-08-13T16:19:05.760
Link: CVE-2026-73558
No data.
OpenCVE Enrichment
Updated: 2026-08-13T18:15:04Z
Weaknesses