Orta CVSS 6.5
CVE-2026-115916: Vllm: güvenlik açığı
Açıklama (NVD)
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.
Özet bilgiler
- Ürün
- Vllm Vllm
- CVSS v3.1
- 6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - EPSS
- %0,31 (yüzdelik 24)
- CWE
- CWE-129
- Yama
- Mevcut
Etkilenen sürümler
| Ürün | Başlangıç | Bitiş | Düzeltildi |
|---|---|---|---|
| vllm-vllm | — | — | 0.32.0 |