Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0.
No analysis available yet.
Remediation
No remediation available yet.
Tracking
Sign in to view the affected projects.
Advisories
No advisories yet.
References
History
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, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0. | |
| Title | vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites) | |
| Weaknesses | CWE-20 CWE-248 CWE-755 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Subscriptions
No data.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-10-05T22:52:05.000Z
Reserved: 2026-10-05T19:11:07.947Z
Link: CVE-2026-105757
No data.
Status : Received
Published: 2026-10-05T23:17:02.467
Modified: 2026-10-05T23:17:02.467
Link: CVE-2026-105757
No data.
OpenCVE Enrichment
No data.