CVE-2026-73559
vLLM: Completion prompt lists fan out into unbounded engine requests
Impact
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 packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | vllm | >= 0.19.0, < 0.26.0 | 0.26.0 |
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Vllm | Vllm | from 0.19.0 before 0.26.0 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/advisories/GHSA-87x5-vmc3-756j
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
- https://nvd.nist.gov/vuln/detail/CVE-2026-73559
- https://github.com/vllm-project/vllm/pull/47845
- https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0