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
cve-program · CVE-2026-93840
PublishedvLLM 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.
- Source published
- 18 Sep 2026 19:06:06 UTC
- Source modified
- 24 Sep 2026 14:23:15 UTC
- Saved here
- 23 Oct 2026 15:48:27 UTC
- Source terms
- CVE Program Terms of Use
Original source record · Cite this exact observation · Complete original publisher JSON
Source: cve-program · CVE Program Terms of Use. The publisher's wording is preserved. ChangeIntel groups the information and labels changes. The JSON record includes additional source fields.
CVSS 4.0 · 6.3 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
CVSS 3.1 · 3.7 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N