CVE-2026-105753
vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core
- State
- Published
- Severity
- 6.5 Medium
- Published
- Oct 5, 2026
- Updated
- Oct 6, 2026
- Reserved
- Oct 5, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 6.5 Medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | GitHub_M |
Weaknesses
- CWE-617 Reachable Assertion
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f
- https://github.com/vllm-project/vllm/pull/46747
- https://github.com/vllm-project/vllm/pull/51897
- https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9
- https://github.com/vllm-project/vllm/releases/tag/v0.28.0
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.