CVE-2025-46570
2 advisories.
PyPI/vllm CVE-2025-46570: low 2.6, EPSS 0.34%
Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching
Action: Upgrade vllm to 0.9.0 or later.
pip install vllm==0.9.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 0.9.0 | - |
Fixed versions
| 0.9.0 |
Sources
- osv: GHSA-4qjh-9fv9-r85r
- https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
- https://nvd.nist.gov/vuln/detail/CVE-2025-46570
- https://github.com/vllm-project/vllm/pull/17045
- https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-53.yaml
- https://github.com/vllm-project/vllm
CVE-2025-46570 · published · modified · JSON
PyPI/vllm CVE-2025-46570: unknown, EPSS 0.34%
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the pref
Action: Upgrade vllm to 0.9.0 or later.
pip install vllm==0.9.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0 | 0.9.0 | - |
Fixed versions
| 0.9.0 |
Sources
- osv: PYSEC-2025-53
- https://github.com/vllm-project/vllm/pull/17045
- https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
- https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
CVE-2025-46570 · published · modified · JSON