CVE-2026-105757 vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)
Attackers can cause a denial of service in vLLM by sending structured-output requests that trigger unhandled exceptions, crashing the shared engine.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-105757?
CVE-2026-105757 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 5 Oct 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-105757?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.30.0 |
vllm PyPI | All versions | 0.30.0 |
vllm PyPI | All versions | 0.30.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-105757?
Upgrade vllm to 0.30.0 or later.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-105757 being exploited?
There is no known exploitation of CVE-2026-105757 in the wild and no public exploit code.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-85xf-c7hm-whqw, MINI-c6hv-9626-wgxg, MINI-c8qj-hf4w-8cp2, MINI-cx8c-m6j2-m62m, PYSEC-2026-4199.