vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.
Advisories
| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-ph72-cqr5-qpp7 | vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features |
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Tue, 06 Oct 2026 00:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vllm-project
Vllm-project vllm |
|
| Vendors & Products |
Vllm-project
Vllm-project vllm |
Mon, 05 Oct 2026 23:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0. | |
| Title | vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features | |
| Weaknesses | CWE-1284 CWE-20 CWE-617 CWE-639 CWE-668 CWE-704 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-10-05T22:46:03.163Z
Reserved: 2026-10-05T19:11:07.947Z
Link: CVE-2026-105754
No data.
Status : Received
Published: 2026-10-05T23:17:02.017
Modified: 2026-10-05T23:17:02.017
Link: CVE-2026-105754
No data.
OpenCVE Enrichment
Updated: 2026-10-06T00:30:18Z
Github GHSA