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
vllm-project vllm
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| vllm PyPI |
|
|
Original 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.
From the CVE record · GitHub_M
References
- github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84fVendor advisory
- github.com/vllm-project/vllm/pull/46747Patch
- github.com/vllm-project/vllm/pull/51897Patch
- github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9Patch
- github.com/vllm-project/vllm/releases/tag/v0.28.0Release notes
- github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105753.json
- nvd.nist.gov/vuln/detail/CVE-2026-105753
- github.com/vllm-project/vllm