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
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924 | Patch |
| https://github.com/vllm-project/vllm/issues/42860 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/pull/49660 | Issue Tracking Patch |
| 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 |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5 | Exploit Vendor Advisory |
Configurations
History
28 Sep 2026, 18:41
| Type | Values Removed | Values Added |
|---|---|---|
| CPE | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | |
| First Time |
Vllm vllm
Vllm |
|
| References | () https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924 - Patch | |
| References | () https://github.com/vllm-project/vllm/issues/42860 - Issue Tracking, Patch | |
| References | () https://github.com/vllm-project/vllm/pull/49660 - Issue Tracking, Patch | |
| References | () https://github.com/vllm-project/vllm/releases/tag/v0.27.0 - Release Notes | |
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5 - Exploit, Vendor Advisory |
Information
Published : 2026-08-13 15:20
Updated : 2026-09-28 18:41
NVD link : CVE-2026-73558
Mitre link : CVE-2026-73558
CVE.ORG link : CVE-2026-73558
JSON object : View
Products Affected
vllm
- vllm
CWE
CWE-190
Integer Overflow or Wraparound