vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids
vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
CVE-2026-93840
Primary source · Revision 1
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-93840
vllm
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
Structured affected-version data
Original package identities and version rules from this source.
[
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "0.29.0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "0.29.0",
"versionType": "semver"
}
],
"packageURL": "pkg:pypi/vllm",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-93840
Source reference:
/cveMetadata/cveId
Publisher severity
medium
Source reference: /containers/cna/metrics
- Event
- #1714 · Revision 1
- Added to Heist Feed
- Publisher date