CVE-2026-105753
vLLM is an inference and serving engine for large language models.
Does this matter?
Lower severity and a low EPSS score (0.43%). 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 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if that request is rejected. A later request reusing the same media hash causes MultiModalProcessorSenderCache to send no payload and MultiModalReceiverCache to reach an assertion with the message "Expected a cached item," producing a shared-service availability failure. This issue is fixed in version 0.28.0.
- CVSS 3.1
- 6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.43% probability · 37th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-617
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
EPSS moved from 0.4% on 6 October 2026 to 0.4% on 26 October 2026.
References
- https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9Patch
- https://github.com/vllm-project/vllm/pull/46747Issue Tracking, Patch
- https://github.com/vllm-project/vllm/pull/51897Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.28.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84fMitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.