vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)
vllm-project vllm
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| vllm PyPI |
|
|
Original 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.
From the CVE record · GitHub_M
References
- github.com/vllm-project/vllm/security/advisories/GHSA-85xf-c7hm-whqwVendor advisory
- github.com/vllm-project/vllm/pull/51450Patch
- github.com/vllm-project/vllm/commit/c55e15a44ec4127832d4a86928a356fdd9e68dbdPatch
- github.com/vllm-project/vllm/releases/tag/v0.30.0Release notes
- github.com/CVEProject/cvelistV5/tree/main/cves/2026/105xxx/CVE-2026-105757.json
- nvd.nist.gov/vuln/detail/CVE-2026-105757
- github.com/vllm-project/vllm