vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
Summary
| CVE | CVE-2026-115916 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-10-26 18:17:39 UTC |
| Updated | 2026-10-26 18:34:17 UTC |
| 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. |
Risk And Classification
Primary CVSS: v3.1 6.5 MEDIUM from [email protected]
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Problem Types: CWE-129 | CWE-193 | CWE-129 CWE-129: Improper Validation of Array Index | CWE-193 CWE-193: Off-by-one Error
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Secondary | 6.5 | MEDIUM | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| 3.1 | CNA | DECLARED | 6.5 | MEDIUM | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
LowPrivileges Required
LowUser Interaction
NoneScope
UnchangedConfidentiality
NoneIntegrity
NoneAvailability
HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | Vllm-project | Vllm | affected < 0.32.0 | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/vllm-project/vllm/releases/tag/v0.32.0 | [email protected] | github.com | |
| github.com/vllm-project/vllm/pull/59491 | [email protected] | github.com | |
| github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf2... | [email protected] | github.com | |
| github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4 | [email protected] | github.com | |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.