vllm-project · vLLM · published 2026-10-26
CVE-2026-115916vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
Routine No exploitation evidence; EPSS 0.3%.
CVE-2026-115916 is not known to be exploited in the wild. EPSS estimates a 0.3% chance of exploitation in the next 30 days, higher than 24% of all CVEs. This vLLM vulnerability: CVSS 6.5 (v3.1). Fixed upstream in vLLM 0.32.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.32.0.
Patch events
AI toolingvLLM
vLLM security release: 0.32.0
Upgrade to
0.32.0Why: Vendor security release for server software (most severe: CVE-2026-94624).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.3% (25th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 6.5 (v3.1)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.32.0(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.