CVE-2026-115916 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

What is CVE-2026-115916?

CVE-2026-115916 is a medium-severity vulnerability in Vllm Vllm, published on 26 Oct 2026.

Official 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.

Weakness: CWE-193, CWE-129

Which versions are affected by CVE-2026-115916?

3 open source packages ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-115916?

Upgrade vllm to 0.32.0 or later.

Is CVE-2026-115916 being exploited?

There is no known exploitation of CVE-2026-115916 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-q97c-p368-75c4, PYSEC-2026-4347.