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.
Affected products
vllm: vllm
References5
- github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg… MitigationVendor Advisory
- github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b… Patch
- github.com/vllm-project/vllm/pull/46747 Issue TrackingPatch
- github.com/vllm-project/vllm/pull/51897 Issue TrackingPatch
- github.com/vllm-project/vllm/releases/tag/v0.28.0 Release Notes
Metrics
- CVSS 3.1
-
6.5
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - EPSS — exploit probability
- 0% percentile: 37 · as of 10 November 2026
- CWE
- CWE-617
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.