Low severityNVD Advisory· Published May 29, 2025· Updated May 29, 2025
vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
CVE-2025-46570
Description
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 prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.9.0 | 0.9.0 |
Affected products
6- osv-coords5 versionspkg:apk/chainguard/py3.10-vllm-cuda-11.8pkg:apk/chainguard/py3.10-vllm-cuda-12.6pkg:apk/chainguard/py3.10-wheels-vllm-cuda-11.8pkg:apk/chainguard/tritonserver-backend-vllm-24.04pkg:pypi/vllm
< 0.9.0-r0+ 4 more
- (no CPE)range: < 0.9.0-r0
- (no CPE)range: < 0.9.0.1-r0
- (no CPE)range: < 0.9.0-r0
- (no CPE)range: < 24.04-r10
- (no CPE)range: < 0.9.0
Patches
Vulnerability mechanics
References
6- github.com/advisories/GHSA-4qjh-9fv9-r85rghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2025-46570ghsaADVISORY
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-53.yamlghsaWEB
- github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54fghsax_refsource_MISCWEB
- github.com/vllm-project/vllm/pull/17045ghsax_refsource_MISCWEB
- github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85rghsax_refsource_CONFIRMWEB
News mentions
0No linked articles in our index yet.