Improper Validation of Array Index Affecting vllm package, versions [,0.32.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-VLLM-21755390
- published27 Oct 2026
- disclosed26 Oct 2026
- creditShijie Lyu
Introduced: 26 Oct 2026
NewCVE-2026-115916 (opens in a new tab)How to fix?
Upgrade vllm to version 0.32.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Improper Validation of Array Index via an off-by-one error in get_cached_tokenizer in vllm/tokenizers/hf.py, where vocab_size (a count) is used directly as the maximum token ID instead of vocab_size - 1. This causes the computed max_token_id to be one greater than the actual largest valid token ID, which can lead to out-of-bounds access or assertion failures during inference, crashing the server.