Vulnerability · Published Oct 26, 2026 · Assigned by GitHub_M
CVE-2026-115916vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
Medium 6.5
In plain English
A medium-severity security flaw in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 24% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.32.0 | GHSA-q97c-p368-75c4 |
| PyPI | vllm | 0.32.0 | PYSEC-2026-4347 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | < 0.32.0 |
Weakness: CWE-129, CWE-193 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4 x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/59491 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229 x_refsource_MISC
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 x_refsource_MISC