CVE-2026-115916
vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
Auswirkung
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.
Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, mit einem normalen Benutzerkonto, ohne Zutun eines Nutzers. Bei Erfolg: hohes Risiko für Ausfälle.
Betroffene Pakete
| Ökosystem | Paket | Betroffen | Behoben in |
|---|---|---|---|
| pip | vllm | < 0.32.0 | 0.32.0 |
Betroffene Produkte
| Hersteller | Produkt | Betroffene Versionen |
|---|---|---|
| Vllm | Vllm | vor 0.32.0 |
| Vllm-project | Vllm | vor 0.32.0 Version < 0.32.0 |
Schwachstellenklasse
Referenzen
- NVD-Eintrag
- CVE.org-Eintrag
- GitHub-Advisory
- https://github.com/advisories/GHSA-q97c-p368-75c4
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4
- https://nvd.nist.gov/vuln/detail/CVE-2026-115916
- https://github.com/vllm-project/vllm/pull/59491
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0