CVE-2026-73558
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…
Does this matter?
Lower severity and a low EPSS score (0.41%). Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 3.1
- 5.3 MEDIUMCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
- EPSS
- 0.41% probability · 35th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-190
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
EPSS 0.4% since 26 October 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.
References
- https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924Patch
- https://github.com/vllm-project/vllm/issues/42860Issue Tracking, Patch
- https://github.com/vllm-project/vllm/pull/49660Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.27.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5Exploit, Vendor Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5Exploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.