CVE-2026-115916
Awaiting Analysis
Awaiting Analysis - Queue
Off-by-One Error in vLLM Tokenizer Validation
Vulnerability report for CVE-2026-115916, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.
Publication date: 2026-10-26
Last updated on: 2026-10-26
Assigner: GitHub, Inc.
Description
Description
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.
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| vllm-project | vllm | < 0.32.0 |
Helpful Resources
Exploitability
CWE
KEV
| CWE ID | Description |
|---|---|
| CWE-193 | A product calculates or uses an incorrect maximum or minimum value that is 1 more, or 1 less, than the correct value. |
| CWE-129 | The product uses untrusted input when calculating or using an array index, but the product does not validate or incorrectly validates the index to ensure the index references a valid position within the array. |
