CVEvulnerability
CVE-2026-73559
6.5 MEDIUM
Official page ↗
- Status
- Analyzed
- Published
- 2026-08-13
- Last modified
- 2026-09-28
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-400
Description
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.
Affected configurations
• vllm vllm (>= 0.19.0 < 0.26.0)
Related
Weakness · CWE (1)
- CWE-400 Uncontrolled Resource Consumption weakness
References
- https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e Patch
- https://github.com/vllm-project/vllm/pull/47845 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j Exploit, Vendor Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j Exploit, Vendor Advisory