vLLM: Completion prompt lists fan out into unbounded engine requests (vllm-project vllm)
At a glance
- Source
- NVD
- EPSS
- EPSS 0.58 % · percentile 48 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Analyzed
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.
Weaknesses (CWE)
- CWE-400 — Uncontrolled Resource Consumption
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | MEDIUM 6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | GitHub_M |
| CVSS 3.1 | MEDIUM 6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | NVD · security-advisories@github.com (Secondary) |
Advisories
- GHSA-87x5-vmc3-756j — vLLM: Completion prompt lists fan out into unbounded engine requests
- PYSEC-2026-3704 — vLLM: Completion prompt lists fan out into unbounded engine requests
European references
- ENISA EUVD · EUVD-2026-58067
- GCVE · GCVE-0-2026-73559
Affected configurations (NVD CPE)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*≥ 0.19.0 < 0.26.0
Affected products
| Product | Versions |
|---|---|
| vllm-project · vllm | affected >= 0.19.0, < 0.26.0 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |