VDB

CVE-2026-105757

CVE-2026-105757 PUBLISHED CVSS 6.5 MEDIUM

Reported by GitHub_M · Published October 5, 2026

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.

Risk Scores

CVSS 3.1
6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Affected Products

VendorProductVersions
vllm-projectvllm< 0.30.0
chainguardvllm-cuda-13.20
vllm-projectvllm0
chainguardvllm-openai-cuda-13.00
chainguardtritonserver-backend-vllm-cuda-13.00
PyPIvllm0

Timeline

  • Oct 5, 2026 CVE Published
  • Oct 6, 2026 EPSS Score
  • Oct 6, 2026 Coalition ESS Score
  • Oct 6, 2026 CVE Updated
  • Oct 8, 2026 EPSS Score
  • Oct 11, 2026 EPSS Score
  • Oct 13, 2026 EPSS Score
  • Oct 14, 2026 EPSS Score
  • Oct 17, 2026 EPSS Score
  • Oct 20, 2026 EPSS Score
  • Oct 21, 2026 EPSS Score
  • Oct 24, 2026 EPSS Score
Open in Interactive Console →
$ Console Community · 50/day Open console ›