CVE-2026-94623

21.09.2026, 22:17

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.

Provider	Type	Base Score	Atk. Vector	Atk. Complexity	Priv. Required	Vector
NIST	Primary	7.5 HIGH	NETWORK	LOW	NONE	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Awaiting analysis

This vulnerability is currently awaiting analysis.

Base Score

CVSS 3.x

EPSS Score

Percentile: Unknown

Common Weakness Enumeration

CWE-617 - Reachable Assertion
The product contains an assert() or similar statement that can be triggered by an attacker, which leads to an application exit or other behavior that is more severe than necessary.

References

https://github.com/vllm-project/vllm

https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/base_worker.py#L2642-L2646

https://github.com/vllm-project/vllm/pull/51505

https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-nixl-multi-prompt-assertion-failure