8.7
High
CVE-2026-94623 vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation…
Description
vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm 0.29 | earliest → 0.29.0 | No fix stated |
References
- Pull Request #51505 github.com
- github.com github.com
- github.com github.com
- VulnCheck Advisory: vLLM through 0.29.0 Denial of Service via NIXL Multi-Prompt Assertion Failure www.vulncheck.com
Timeline
- Published
- Last modified
Other CVEs of vllm
The 121 CVEs of vllm →
CVE-2026-115918
vLLM is an inference and serving engine for large language models
6.5
Medium
CVE-2026-115917
vLLM is an inference and serving engine for large language models
3.4
Low
CVE-2026-115916
vLLM is an inference and serving engine for large language models
6.5
Medium
CVE-2026-115915
vLLM is an inference and serving engine for large language models
8.1
High