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
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.
INFO
Published Date :
Oct. 5, 2026, 11:17 p.m.
Last Modified :
Oct. 5, 2026, 11:17 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | MEDIUM | MITRE-CVE | ||||
| CVSS 3.1 | MEDIUM | [email protected] |
Solution
- Update vLLM to version 0.28.0.
- Ensure all deployments use the patched version.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-105753.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-105753 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-105753
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-105753 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-105753 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Oct. 05, 2026
Action Type Old Value New Value Added 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. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Added CWE CWE-617 Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/105xxx/CVE-2026-105753.json">CVE-2026-105753</a> Added Reference https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9 Added Reference https://github.com/vllm-project/vllm/pull/46747 Added Reference https://github.com/vllm-project/vllm/pull/51897 Added Reference https://github.com/vllm-project/vllm/releases/tag/v0.28.0 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f