vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids
Historical advisory recorded 23 Oct 2026 15:48:27 UTC. Read the latest advisory.
cve-program · CVE-2026-93840
PublishedvLLM 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.
Read the publisher's advisoryAffected versions, risk and source history
Related advisories and sources
Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.
CVE-2026-93840 · CVE overview and exploitation status
cve-program · CVE-2026-93840
- 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
This historical advisory does not include today's related changes. Open the latest advisory to find current connections.