CVE-2025-29770 vLLM denial of service via outlines unbounded cache on disk
Attackers can cause denial of service in vLLM by exhausting disk space through unbounded caching of unique schemas in the outlines backend.
- 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-2025-29770?
CVE-2025-29770 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 19 Mar 2025. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the OpenAI compatible API server. The affected code in vLLM is vllm/model_executor/guided_decoding/outlines_logits_processors.py, which unconditionally uses the cache from outlines. A malicious user can send a stream of very short decoding requests with unique schemas, resulting in an addition to the cache for each request. This can result in a Denial of Service if the filesystem runs out of space. Note that even if vLLM was configured to use a different backend by default, it is still possible to choose outlines on a per-request basis using the guided_decoding_backend key of the extra_body field of the request. This issue applies only to the V0 engine and is fixed in 0.8.0.
Weakness: CWE-770
Which versions are affected by CVE-2025-29770?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.8.0 |
vllm PyPI | All versions | 0.8.0 |
vllm PyPI | All versions | 0.8.0 |
Products include Vllm Vllm.
How do I fix CVE-2025-29770?
Upgrade vllm to 0.8.0 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-2025-29770 being exploited?
There is no known exploitation of CVE-2025-29770 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-mgrm-fgjv-mhv8, PYSEC-2025-223.