Description
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.
No analysis available yet.
Remediation
No remediation available yet.
Tracking
Sign in to view the affected projects.
Advisories
No advisories yet.
References
History
Fri, 18 Sep 2026 21:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | 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. | |
| Title | vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids | |
| First Time appeared |
Vllm
Vllm vllm |
|
| Weaknesses | CWE-129 | |
| CPEs | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | |
| Vendors & Products |
Vllm
Vllm vllm |
|
| References |
|
|
| Metrics |
cvssV3_1
|
Status: PUBLISHED
Assigner: VulnCheck
Published:
Updated: 2026-09-18T19:06:06.001Z
Reserved: 2026-09-18T18:16:47.489Z
Link: CVE-2026-93840
No data.
Status : Received
Published: 2026-09-18T20:17:34.200
Modified: 2026-09-18T20:17:34.200
Link: CVE-2026-93840
No data.
OpenCVE Enrichment
No data.
Weaknesses
-
CWE-129
Improper Validation of Array Index