CVE-2026-73558
published 2026-08-13CVE-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…
PriorityP428medium5.3CVSS 3.1
AVNACHPRNUIRSUCHINAN
EPSS
0.26%
18.0th percentile
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
1 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| vllm-project | vllm | < 0.27.0 | 0.27.0 |
CVSS provenance
nvdv3.15.3MEDIUMCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
vendor_redhat5.3MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
VulDB
vllm-project vLLM up to 0.26.x Activation Kernels activation_kernels.cu act_and_mul_kernel integer overflow (WID-SEC-2026-2842)
vuldb·2026-08-16·CVSS 5.3
CVE-2026-73558 [MEDIUM] vllm-project vLLM up to 0.26.x Activation Kernels activation_kernels.cu act_and_mul_kernel integer overflow (WID-SEC-2026-2842)
A vulnerability classified as problematic was found in vllm-project vLLM up to 0.26.x. The affected element is the function act_and_mul_kernel of the file activation_kernels.cu of the component Activation Kernels. Such manipulation leads to integer overflow.
This vulnerability is listed as CVE-2026-73558. The attack may be performed from remote. There is no available exploit.
Upgrading the affected component is advised.
Red Hat
vllm: vLLM: Cross-User Data Leakage via Integer Overflow
vendor_redhat·2026-08-13·CVSS 5.3
CVE-2026-73558 [MEDIUM] CWE-190 vllm: vLLM: Cross-User Data Leakage via Integer Overflow
vllm: vLLM: Cross-User Data Leakage via Integer Overflow
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.
A flaw was found in vLLM, an inference and serving engine for large language models. An integer overflow vulnerability in the `act_and_mul_kernel` kernel allows a remote attacker to cause cross-user data leakage. By crafting specific requests processed in the same inference batch, an attacker can obtain a partial or complete copy of another user's
No detection rules found.
No public exploits indexed.
https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924https://github.com/vllm-project/vllm/issues/42860https://github.com/vllm-project/vllm/pull/49660https://github.com/vllm-project/vllm/releases/tag/v0.27.0https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
2026-08-13
Published