CVE-2026-105753

01/תיאור (מקור, אנגלית)

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.

02/מוצרים מושפעים

vllm: vllm

03/קישורים5

• github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jf‮… MitigationVendor Advisory
• github.com/vllm-project/vllm/commit/396204230423b7cc6798300926‮… 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