Bug 2515421 (CVE-2026-73559)

Summary: CVE-2026-73559 vllm: vLLM: Denial of Service via unbounded completion prompt lists
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security <prodsec-ir-bot>
Status: NEW --- QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: unspecifiedCC: alinfoot, bbrownin, dtrifiro, rbryant, weaton
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
A flaw was found in vLLM, an inference and serving engine for large language models. An authenticated API client can exploit this vulnerability by sending a single request to the /v1/completions endpoint with an excessively large list of prompts. This unbounded input causes the vLLM server to allocate a disproportionate amount of CPU, memory, and other resources, leading to a Denial of Service (DoS) condition. This can disrupt or starve other services sharing the same vLLM instance.
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-08-13 16:04:24 UTC
vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.