CVSS 3.1
6.5 mediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:HCVE-2026-73559
Medium (6.5) in vllm vllm. EPSS 0.6% chance of exploitation in the next 30 days. Fixed in vllm 0.26.0.
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.
Severity
- EPSS
- 0.6% chance of exploitation in the next 30 days; higher than 47% of CVEs (scores of 2026-10-31)
- CWE
- CWE-400
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-87x5-vmc3-756j | PyPI | vllm | >=0.19.0 <0.26.0 | 0.26.0 |
| PYSEC-2026-3704 | PyPI | vllm | >=0.19.0 <0.26.0 | 0.26.0 |
References
- https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
- https://github.com/vllm-project/vllm/pull/47845
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j