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

Published Oct 5, 2026 CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

The defect lies in vLLM's mirrored multimodal IPC cache. When a multimodal request that references a media hash is rejected before the engine admits it, the frontend sender cache records the hash but the engine receiver cache never receives the payload. A later request that reuses the same hash forces the sender cache to transmit nothing while the receiver cache hit an assertion with the message "Expected a cached item", which causes the vLLM service to crash. This flaw manifests as a buffer consistency bug between caching components and is classified as CWE-617.

Affected Systems

vLLM, the inference and serving engine for large language models released by vllm-project, is affected. All installations running any version prior to 0.28.0 are vulnerable; no other vendors or products are listed as impacted.

Risk and Exploitability

The CVSS score of 6.5 indicates moderate severity due to denial‑of‑service potential. The EPSS score is not available and the vulnerability is not listed in the CISA KEV catalog, suggesting limited evidence of exploitation to date. The likely attack vector is inferred to be the network interface of the vLLM service, requiring the ability to send crafted multimodal requests to the endpoint. An attacker can repeatedly send rejected requests that reuse the same media hash, eventually triggering the assertion and terminating the service, affecting all users sharing the instance.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade vLLM to version 0.28.0 or later, which contains the fix.
  • Monitor service logs for the assertion message "Expected a cached item" and configure an automated restart or graceful recovery to minimize downtime.
  • Re‑run tests that submit a rejected multimodal request followed by a repeated request with the same media hash to confirm the vulnerability is no longer triggered.

Generated by OpenCVE AI on October 5, 2026 at 23:50 UTC.

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Github GHSA Github GHSA GHSA-ph3r-5jfg-f84f 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
History
Type Values Removed Values Added
First Time appeared Vllm
Vllm vllm
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm
Type Values Removed Values 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.
Title 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
Weaknesses CWE-617
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Oct 6, 2026, 1:23 PM
Reserved
Oct 5, 2026, 7:11 PM
Status
Analyzed
Published
Oct 5, 2026, 11:17 PM
Modified
Oct 8, 2026, 1:29 AM
Severity
Moderate
Public date
Oct 5, 2026, 10:37 PM