CVE-2025-29770
published 2025-03-19CVE-2025-29770: 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…
PriorityP335medium6.5CVSS 3.1
AVNACLPRLUINSUCNINAH
EPSS
0.42%
33.7th percentile
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.
Affected
3 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| vllm-project | vllm | < 0.8.0 | 0.8.0 |
| vllm | vllm | < 0.8.0 | 0.8.0 |
| vllm | vllm | >= 0 < 0.8.0 | 0.8.0 |
CVSS provenance
nvdv3.16.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
vendor_redhat6.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
OSV
vLLM denial of service via outlines unbounded cache on disk
osv·2025-03-19
CVE-2025-29770 [MEDIUM] vLLM denial of service via outlines unbounded cache on disk
vLLM denial of service via outlines unbounded cache on disk
### Impact
The [outlines](https://dottxt-ai.github.io/outlines/latest/) 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](https://github.com/vllm-project/vllm/blob/53be4a863486d02bd96a59c674bbec23eec508f6/vllm/model_executor/guided_decoding/outlines_logits_processors.py), which unconditionally uses the cache from outlines. vLLM should have this off by default and allow administra
GHSA
vLLM denial of service via outlines unbounded cache on disk
ghsa·2025-03-19
CVE-2025-29770 [MEDIUM] CWE-770 vLLM denial of service via outlines unbounded cache on disk
vLLM denial of service via outlines unbounded cache on disk
### Impact
The [outlines](https://dottxt-ai.github.io/outlines/latest/) 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](https://github.com/vllm-project/vllm/blob/53be4a863486d02bd96a59c674bbec23eec508f6/vllm/model_executor/guided_decoding/outlines_logits_processors.py), which unconditionally uses the cache from outlines. vLLM should have this off by default and allow administra
Red Hat
vllm: vLLM denial of service via outlines unbounded cache on disk
vendor_redhat·2025-03-19·CVSS 6.5
CVE-2025-29770 [MEDIUM] CWE-770 vllm: vLLM denial of service via outlines unbounded cache on disk
vllm: vLLM denial of service via outlines unbounded cache on disk
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 Se
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2025-03-19
Published