← Back to CVE List
CVE-2026-93840NVD
Vulnerability Summary
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.
CVSS v3.1 Base Metrics
Attack VectorNetwork
Attack ComplexityHigh
Privileges RequiredNone
User InteractionNone
ScopeUnchanged
ConfidentialityNone
IntegrityLow
AvailabilityNone
External References
- https://github.com/vllm-project/vllm/pull/49080
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/commit/5b0e5b69ac1a3884a6479c9537789c95263cc804
- https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/sampling_params.py#L881-L903
- https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/v1/worker/gpu/sample/logit_bias.py#L179-L191
- https://www.vulncheck.com/advisories/vllm-before-0.29.0-cross-request-logits-corruption-via-allowed-token-ids