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.
01
beschreibt (1)
Zugehörige CVEs.
| ID | Schweregrad | ausnutzbar | ||
|---|---|---|---|---|
| CVE-2026-94623US | high7.5 | — | ||
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-promp… | ||||
02
Referenzen
Externe Belege — Patches, Meldungen, Analysen.
- https://github.com/vllm-project/vllmPACKAGE
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/base_worker.py#L2642-L2646WEB
- https://github.com/vllm-project/vllm/pull/51505FIX
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-nixl-multi-prompt-assertion-failureADVISORY
scry
Advisories wie diese benennen die exponierten Produkte, die Angreifer auf Ihrer Angriffsfläche ins Visier nehmen. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan