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
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 software
Click a technology to see all vulnerabilities affecting it.
| Platform | Package | Vulnerable versions | Fixed in |
|---|---|---|---|
| Python (PyPI) | vllm | < 0.32.0 | 0.32.0 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4
- https://nvd.nist.gov/vuln/detail/CVE-2026-115916
- https://github.com/vllm-project/vllm/pull/59491
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H- Weakness (CWE)
CWE-129, CWE-193- Platform
- Python (PyPI)
- Package
vllm- Disclosed
- 26.10.2026
- Updated
- 29.10.2026 12:17
Sources and licenses
OSV / GitHub Advisory Database - GHSA-q97c-p368-75c4 - CC BY 4.0
OSV / GitHub Advisory Database - PYSEC-2026-4347 - PyPA Advisory Database; CC BY 4.0
Vulnerability history: vllm
All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.
- Total entries
- 107
- First → latest
- 09.2024 10.2026
- Without a fix
- 5
- Exploited in attacks
- 0
Severity breakdown
- Critical 10
- High 25
- Medium 55
- Low 4
- Unrated 13
Disclosures per year
- 2024: 2
- 2025: 30
- 2026: 75
-
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 this entry
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.