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 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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-105753
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 8 Nov 2026, 02:03 UTC · Revision 1
Source evidence
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
core-osv · Original sourcePublished 5 Oct 2026, 22:37 UTC
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.
osv:CVE-2026-105753
Complete source record
{
"id": "81b0f88f904555c9cf7c597c78b05476b20dfc7097e6be0f53049d8b178553f2",
"url": "https://osv.dev/vulnerability/CVE-2026-105753",
"method": "structured",
"payload": {
"kind": "advisory",
"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",
"summary": "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.",
"evidence": "osv:CVE-2026-105753",
"products": [],
"severity": "medium",
"structured": {
"id": "CVE-2026-105753",
"aliases": [
"CVE-2026-105753",
"GHSA-ph3r-5jfg-f84f",
"PYSEC-2026-4197"
],
"metrics": [
{
"type": "CVSS_V3",
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/vllm-project/vllm",
"type": "GIT",
"events": [
{
"introduced": "0"
},
{
"fixed": "2cf0a6915ce544dc493a0990f2ea38d81601128a"
},
{
"fixed": "396204230423b7cc6798300926b8fa30190d26a9"
}
],
"database_specific": {
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "0.28.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "396204230423b7cc6798300926b8fa30190d26a9"
}
],
"source": "REFERENCES_COMMIT"
},
{
"range": [
{
"fixed": "2cf0a6915ce544dc493a0990f2ea38d81601128a"
}
],
"source": "REFERENCES_TAG",
"original_tag": "v0.28.0"
}
]
}
}
],
"versions": [
"v0.26.1rc0",
"v0.25.0",
"v0.23.1rc0",
"v0.22.1rc0",
"v0.21.1rc0",
"v0.20.2rc0",
"v0.20.1rc0",
"v0.19.2rc0",
"v0.19.1rc0",
"v0.18.2rc0",
"v0.18.1rc0",
"v0.17.2rc0",
"v0.18.0rc0",
"v0.17.1rc0",
"v0.17.0rc0",
"v0.16.0rc1",
"v0.15.2rc0",
"v0.16.0rc0",
"v0.15.0rc1",
"v0.14.0rc1",
"v0.14.0rc0",
"v0.13.0rc1",
"v0.11.1",
"v0.11.1rc6",
"v0.11.1rc5",
"v0.11.1rc4",
"v0.11.1rc3",
"v0.11.1rc2",
"v0.11.1rc1",
"v0.11.1rc0",
"v0.11.0rc1",
"v0.10.2rc2",
"v0.10.2rc1",
"v0.10.1rc1",
"v0.10.0rc2",
"v0.10.0",
"v0.10.0rc1",
"v0.9.2rc1",
"v0.9.1rc2",
"v0.9.1",
"v0.9.1rc1",
"v0.9.0",
"v0.8.4",
"v0.8.3rc1",
"v0.8.2",
"v0.8.1",
"v0.8.0rc2",
"v0.8.0rc1",
"v0.7.3",
"v0.7.2",
"v0.7.1",
"v0.7.0",
"v0.6.6.post1",
"v0.6.6",
"v0.6.5",
"v0.6.4.post1",
"v0.6.4",
"v0.6.3.post1",
"v0.6.3",
"v0.6.2",
"v0.6.1.post2",
"v0.6.1.post1",
"v0.6.1",
"v0.6.0",
"v0.5.5",
"v0.5.4",
"v0.5.3.post1",
"v0.5.3",
"v0.5.2",
"v0.5.1",
"v0.5.0.post1",
"v0.5.0",
"v0.4.3",
"v0.4.2",
"v0.4.1",
"v0.4.0.post1",
"v0.4.0",
"v0.3.3",
"v0.3.2",
"v0.3.1",
"v0.3.0",
"v0.2.7",
"v0.2.6",
"v0.2.5",
"v0.2.4",
"v0.2.3",
"v0.2.2",
"v0.2.1",
"v0.2.0",
"v0.1.7",
"v0.1.6",
"v0.1.5",
"v0.1.4",
"v0.1.3",
"v0.1.2",
"v0.1.1",
"v0.1.0",
"submission"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-105753.json"
}
}
],
"modified": "2026-10-28T02:30:52.759531142Z",
"provider": "osv",
"references": [
"https://github.com/vllm-project/vllm/releases/tag/v0.28.0",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105753.json",
"https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f",
"https://nvd.nist.gov/vuln/detail/CVE-2026-105753",
"https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9",
"https://github.com/vllm-project/vllm/pull/46747",
"https://github.com/vllm-project/vllm/pull/51897"
],
"provider_metadata": {
"cwe_ids": [
"CWE-617"
],
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105753.json"
}
},
"related_cves": [
{
"value": "CVE-2026-105753",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 521604,
"published_at": "2026-10-05T22:37:19.633+00:00"
}