CVEvulnerability
CVE-2026-105757
6.5 MEDIUM
Official page ↗
- Status
- Analyzed
- Published
- 2026-10-05
- Last modified
- 2026-10-08
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-20, CWE-248, CWE-755
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.
Affected configurations
• vllm vllm (< 0.30.0)
Related
References
- https://github.com/vllm-project/vllm/commit/c55e15a44ec4127832d4a86928a356fdd9e68dbd Patch
- https://github.com/vllm-project/vllm/pull/51450 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-85xf-c7hm-whqw Mitigation, Vendor Advisory