Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| vllm-project / vllm | affected 0 before 0.29.0; unaffected 0.29.0 |
CWE
CWE-129
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
ADP enrichment
No English description supplied.
No references supplied.