CVE-2026-105753
PYSEC-2026-4197 · CVE-2026-105753 · GHSA-ph3r-5jfg-f84f
Published · Modified
AI SAST
Find this class of vulnerability in your own code
Corgea's AI-native static analysis detects vulnerabilities like this one across your repositories, ranks them by exploitability, and returns review-ready fixes.
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.
References
- ADVISORY https://github.com/vllm-project/vllm/releases/tag/v0.28.0
- ADVISORY https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f
- FIX https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9
- FIX https://github.com/vllm-project/vllm/pull/46747
- FIX https://github.com/vllm-project/vllm/pull/51897
Ready to move
Start Securing
Free, no credit card | First findings in minutes